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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verse
    -0.06
     Johannesburg
    -0.06
     clipped
    -0.06
    FTA
    -0.06
     six
    -0.06
     مراجع
    -0.06
     thr
    -0.05
    _sat
    -0.05
    finity
    -0.05
    hawk
    -0.05
    POSITIVE LOGITS
    　
    0.08
     lasc
    0.08
     thừa
    0.07
    衆
    0.07
     Spacer
    0.07
    .ColumnName
    0.07
    .engine
    0.07
    _DISABLE
    0.06
     _↵
    0.06
     Raptors
    0.06
    Act Density 0.002%

    No Known Activations