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

    Neuronpedia

    INDEX
    Explanations

    words that express admiration or highlight outstanding qualities

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

    Figurative use of nouns

    np_acts-logits-general · gemini-2.0-flash

    noteworthy things or people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "]="
    -0.45
    AnchorStyles
    -0.44
     fortement
    -0.44
    endphp
    -0.43
     "..\..\
    -0.43
    IM
    -0.43
     hyvin
    -0.43
    例文帳に追加
    -0.42
    ",@"
    -0.41
     graciosas
    -0.41
    POSITIVE LOGITS
    rrggbb
    0.86
     incarnate
    0.78
    DeleteBehavior
    0.78
    AsUp
    0.75
    StructEnd
    0.74
    ">*</
    0.74
     nhàng
    0.73
    uxxxx
    0.73
    Externé
    0.69
    ducers
    0.67
    Act Density 0.333%

    No Known Activations