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

    Neuronpedia

    INDEX
    Explanations

    structured programming constructs and syntax elements

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

    user turn initiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unbearable
    -0.30
    endmodule
    -0.29
     кӀош
    -0.29
    sudo
    -0.29
     voisin
    -0.28
    èces
    -0.27
     مؤ
    -0.26
     Kanton
    -0.26
     sugiere
    -0.26
    install
    -0.25
    POSITIVE LOGITS
     ProtoMessage
    0.74
     समीक्षाओं
    0.72
     betweenstory
    0.70
    SharedDtor
    0.68
    нгред
    0.63
    تقاوى
    0.63
    SequentialGroup
    0.62
    хьтан
    0.61
    <unused42>
    0.60
    <unused68>
    0.60
    Act Density 0.004%

    No Known Activations