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

    Neuronpedia

    INDEX
    Explanations

    Method

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jill
    -0.07
     kz
    -0.07
     Zur
    -0.07
    ……………………
    -0.07
     videot
    -0.07
    tgt
    -0.07
    _ME
    -0.07
    _St
    -0.07
     enlight
    -0.07
    (encoder
    -0.06
    POSITIVE LOGITS
    .Duration
    0.08
     swiftly
    0.07
    illos
    0.07
    几个人
    0.06
    먄
    0.06
    (diff
    0.06
     barrel
    0.06
    ft
    0.06
    ommen
    0.06
    德尔
    0.06
    Act Density 0.000%

    No Known Activations