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

    Neuronpedia

    INDEX
    Explanations

    days of the week

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.84
     للمعارف
    -0.83
    InputBorder
    -0.81
    HostException
    -0.80
    jooq
    -0.79
    posedge
    -0.78
    脚注の使い方
    -0.77
    httphttps
    -0.76
    '])){
    -0.76
    SharedDtor
    -0.73
    POSITIVE LOGITS
     is
    0.65
     it
    0.53
     (
    0.53
     you
    0.52
     all
    0.52
     I
    0.49
     p
    0.48
     b
    0.48
     we
    0.46
     a
    0.46
    Act Density 0.026%

    No Known Activations