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

    Neuronpedia

    INDEX
    Explanations

    extracted data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     --------------------
    -0.06
     sapi
    -0.06
     consec
    -0.06
     eros
    -0.06
     vign
    -0.06
    sexo
    -0.06
    SEQ
    -0.06
     adjacent
    -0.06
     secre
    -0.06
    .Enqueue
    -0.06
    POSITIVE LOGITS
    망
    0.06
    meet
    0.06
    歳
    0.06
     gönder
    0.06
    이트
    0.06
    _least
    0.06
    odel
    0.06
    ेकर
    0.06
    -stock
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations