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

    Neuronpedia

    INDEX
    Explanations

    Java

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    انی
    -0.08
     cops
    -0.08
    EO
    -0.07
    PT
    -0.07
     provider
    -0.06
    _formatted
    -0.06
    取消
    -0.06
     detective
    -0.06
    _acc
    -0.06
    ันย
    -0.06
    POSITIVE LOGITS
    )\<
    0.07
    _PICTURE
    0.06
     Aud
    0.06
     Jedi
    0.06
    employment
    0.06
    .Excel
    0.06
     Consum
    0.06
    imiz
    0.06
    (numbers
    0.06
     новый
    0.05
    Act Density 0.001%

    No Known Activations