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

    Neuronpedia

    INDEX
    Explanations

    software development mailing lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (check
    -0.07
     divides
    -0.07
     Тер
    -0.07
    _account
    -0.07
     standardized
    -0.06
    을
    -0.06
     lowest
    -0.06
     eine
    -0.06
    ◎
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     دقیقه
    0.06
    rid
    0.06
    RID
    0.06
     ****************************************************************************
    0.06
     vod
    0.06
    toggleClass
    0.06
    _SM
    0.05
     gr
    0.05
    OrFail
    0.05
    oples
    0.05
    Act Density 0.079%

    No Known Activations