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

    Neuronpedia

    INDEX
    Explanations

    classification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _OWNER
    -0.07
    SuccessListener
    -0.06
    裂
    -0.06
    (wallet
    -0.06
     جشن
    -0.06
     vận
    -0.06
    幅
    -0.06
    ��
    -0.06
    (epoch
    -0.06
    .rm
    -0.06
    POSITIVE LOGITS
     consumes
    0.07
    .Gr
    0.07
     Except
    0.07
    isecond
    0.06
     kang
    0.06
     incapable
    0.06
     Formatter
    0.06
    forced
    0.06
    )m
    0.06
     Jen
    0.06
    Act Density 0.012%

    No Known Activations