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

    Neuronpedia

    INDEX
    Explanations

    code syntax and structure elements in programming language text

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

    variable name followed by colon or equals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ruptedException
    -0.36
    PutMapping
    -0.35
     fre
    -0.34
     volante
    -0.34
    憾
    -0.33
    TabStop
    -0.33
    ExtendWith
    -0.32
    ября
    -0.32
    solved
    -0.32
    もの
    -0.32
    POSITIVE LOGITS
     name
    1.20
     names
    1.09
     Name
    1.07
    rungsseite
    1.04
     NAME
    1.04
     Namen
    1.02
    Name
    1.02
     Names
    1.02
    name
    0.94
     namn
    0.94
    Act Density 0.041%

    No Known Activations