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

    Neuronpedia

    INDEX
    Explanations

    thrift

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    停车
    -0.07
     culo
    -0.07
    Verify
    -0.07
    榆林
    -0.07
     miss
    -0.07
    קרא
    -0.07
    打扫
    -0.07
    载
    -0.07
    用餐
    -0.07
     irrespective
    -0.07
    POSITIVE LOGITS
    riority
    0.07
    oble
    0.07
    ович
    0.07
     tgt
    0.07
     б
    0.07
     gs
    0.07
    큠
    0.07
    ogui
    0.06
    ㉱
    0.06
    ʵ
    0.06
    Act Density 0.006%

    No Known Activations