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

    Neuronpedia

    INDEX
    Explanations

    rehearsal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     billionaires
    -0.07
    .dat
    -0.06
    驱
    -0.06
    gado
    -0.06
    �藏
    -0.06
    附
    -0.06
     度
    -0.06
    omin
    -0.06
    博
    -0.06
    _MSK
    -0.06
    POSITIVE LOGITS
     surgical
    0.07
     polarization
    0.07
     Thực
    0.07
     Все
    0.07
    имв
    0.06
    (TRUE
    0.06
     intro
    0.06
     resting
    0.06
    (Math
    0.06
    -pane
    0.06
    Act Density 0.007%

    No Known Activations