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

    Neuronpedia

    INDEX
    Explanations

    code snippets and programming constructs in a document

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

    python code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.73
     autorytatywna
    -0.54
     Италијани
    -0.53
     ProtoMessage
    -0.52
    CrossRef
    -0.50
     Taktlose
    -0.50
     pinulongan
    -0.50
    WriteBarrier
    -0.49
     ISNI
    -0.49
    ToBounds
    -0.47
    POSITIVE LOGITS
    "}")
    0.46
     snip
    0.45
    acon
    0.45
    }}}}
    0.45
     الإن
    0.44
    abase
    0.44
    pide
    0.42
    gegen
    0.42
    ako
    0.42
    asis
    0.42
    Act Density 0.021%

    No Known Activations