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

    Neuronpedia

    INDEX
    Explanations

    segments of code and mathematical expressions

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

    sequences of numbers like 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UVWXYZ
    -0.54
    fully
    -0.54
     ролях
    -0.53
     оригіналу
    -0.48
    +#+
    -0.48
     AssemblyCompany
    -0.46
    Зноскі
    -0.46
    FULLY
    -0.44
    ulemon
    -0.43
    PYX
    -0.42
    POSITIVE LOGITS
    uxxxx
    0.56
     gynhyrchwyd
    0.40
     Taktlose
    0.36
    intios
    0.35
    IsMutable
    0.35
     TextInputType
    0.35
     wusste
    0.34
     zand
    0.33
     '\\;'
    0.33
    0.31
    Act Density 0.476%

    No Known Activations