Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    various coding and programming constructs, including symbols and syntax commonly used in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, symbols, and special characters

    np_acts-logits-general · gemini-2.0-flash

    airport descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feroit
    -0.36
     vatten
    -0.34
     Ruang
    -0.32
     avoient
    -0.32
     trouvez
    -0.31
     communs
    -0.31
     abuela
    -0.31
     ngunit
    -0.31
     kteří
    -0.31
     ingresos
    -0.31
    POSITIVE LOGITS
     [*]
    5.22
    [*]
    1.34
     оригіналу
    0.93
    ंदीखरीदारी
    0.92
     BoxFit
    0.91
     AssemblyCompany
    0.87
     ***!
    0.86
    Personendaten
    0.84
    WriteBarrier
    0.84
     AssemblyVersion
    0.83
    Act Density 0.150%

    No Known Activations