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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Shar
    -0.07
     yourself
    -0.07
    .mat
    -0.07
     Shar
    -0.06
     之
    -0.06
     Tensor
    -0.06
     AO
    -0.06
     Break
    -0.06
     themselves
    -0.06
    Ice
    -0.06
    POSITIVE LOGITS
    _NONNULL
    0.07
    }()↵↵
    0.07
    .grade
    0.06
    abama
    0.06
     yaşan
    0.06
    .getTable
    0.06
    UIButton
    0.06
    ерів
    0.06
     갤로그로
    0.06
    :')↵
    0.06
    Act Density 0.095%

    No Known Activations