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

    Neuronpedia

    INDEX
    Explanations

    the word 'to' with words expressing emotion

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endphp
    -0.55
    出版年
    -0.52
    LikeLiked
    -0.50
    ADELPHIA
    -0.48
    Gambas
    -0.47
     AttributeSet
    -0.47
    PyExc
    -0.47
    HomeAsUpEnabled
    -0.46
    LikeLike
    -0.46
    <!--[
    -0.46
    POSITIVE LOGITS
    parsedMessage
    0.77
    لينكات
    0.64
     have
    0.60
    Personensuche
    0.60
     see
    0.60
     receive
    0.59
     recieve
    0.59
    InvalidProtocol
    0.56
    astă
    0.54
     كومونز
    0.54
    Act Density 0.643%

    No Known Activations