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

    Neuronpedia

    INDEX
    Explanations

    liable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Except
    -0.07
    实事
    -0.07
    庶
    -0.07
    を使
    -0.07
    نزل
    -0.06
     можно
    -0.06
    ળ
    -0.06
    Published
    -0.06
    ກ
    -0.06
    都被
    -0.06
    POSITIVE LOGITS
    ifferential
    0.08
     ids
    0.07
     demonstrators
    0.07
     фор
    0.07
    OAD
    0.07
     wraps
    0.06
    規定
    0.06
     hare
    0.06
    tries
    0.06
    รถย
    0.06
    Act Density 0.009%

    No Known Activations