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

    Neuronpedia

    INDEX
    Explanations

    code-related terminology and structures

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

    object declarations and assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.81
    ⩴
    -0.80
    ſammen
    -0.73
    transQ
    -0.73
     $_(
    -0.71
    <unused42>
    -0.71
    <unused71>
    -0.71
    <unused79>
    -0.71
    <unused43>
    -0.71
    [@BOS@]
    -0.71
    POSITIVE LOGITS
     nahilalakip
    0.39
     und
    0.28
     móveis
    0.27
     OMITBAD
    0.24
     and
    0.22
    /**
    0.22
    [toxicity=0]
    0.22
     ProtoMessage
    0.22
    endaft
    0.22
    在
    0.21
    Act Density 0.018%

    No Known Activations