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

    Neuronpedia

    INDEX
    Explanations

    Expressing satisfaction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     livestock
    -0.06
    _finalize
    -0.06
     steht
    -0.06
    ieran
    -0.06
     thermometer
    -0.06
    Markers
    -0.06
     Jacobs
    -0.06
    Tumblr
    -0.06
     คำ
    -0.06
     pearl
    -0.06
    POSITIVE LOGITS
    getColor
    0.07
     行政
    0.06
     confisc
    0.06
    ーブ
    0.06
    Dec
    0.06
    اتف
    0.06
     البل
    0.06
    �
    0.06
    instein
    0.06
     �
    0.06
    Act Density 0.070%

    No Known Activations