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

    Neuronpedia

    INDEX
    Explanations

    every

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reduced
    -0.07
     муз
    -0.07
     Clin
    -0.07
    .Ref
    -0.07
    _pick
    -0.07
     Basic
    -0.06
     Yüksek
    -0.06
    ULONG
    -0.06
     wenig
    -0.06
    .scene
    -0.06
    POSITIVE LOGITS
     κάθε
    0.07
     every
    0.07
     each
    0.07
    every
    0.07
    )))));
↵
    0.06
     educate
    0.06
    ятно
    0.06
    '})
    0.06
    ()));
    0.06
    )a
    0.06
    Act Density 0.012%

    No Known Activations