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

    Neuronpedia

    INDEX
    Explanations

    references to external entities or locations beyond a specified group or context

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

    "outside"

    np_acts-logits-general · gemini-2.0-flash

    outside a boundary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Various
    -0.51
     different
    -0.49
    Downloads
    -0.48
    Various
    -0.48
    Different
    -0.45
     Different
    -0.45
    different
    -0.45
     real
    -0.45
    NotEmpty
    -0.44
     various
    -0.43
    POSITIVE LOGITS
    encodeWith
    0.87
    AndEndTag
    0.83
    URLException
    0.83
     ModelExpression
    0.83
    yntaxException
    0.77
     تضيفلها
    0.76
    GraphicsUnit
    0.72
     Мексичка
    0.72
    CloseOperation
    0.69
     <=",
    0.67
    Act Density 0.431%

    No Known Activations