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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    401
    -0.07
     Replies
    -0.07
    东省
    -0.06
    These
    -0.06
     withdrawal
    -0.06
    ライ
    -0.06
     RequestMethod
    -0.06
     included
    -0.06
    บค
    -0.06
    회
    -0.06
    POSITIVE LOGITS
     Dub
    0.07
     Jupiter
    0.07
    (nome
    0.07
     PASSWORD
    0.07
     mistakenly
    0.07
    _mk
    0.06
    殊
    0.06
     urine
    0.06
    田
    0.06
    abbreviation
    0.06
    Act Density 0.000%

    No Known Activations