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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     th�
    -0.07
    _TRA
    -0.07
    .prototype
    -0.06
     Foto
    -0.06
    없
    -0.06
    esso
    -0.06
    817
    -0.06
    xfff
    -0.06
    ені
    -0.06
     сказал
    -0.06
    POSITIVE LOGITS
    しよう
    0.07
     сфері
    0.06
     Rewrite
    0.06
    {};↵
    0.06
    -variable
    0.06
     fasting
    0.06
     Birthday
    0.06
    Defines
    0.06
     constructing
    0.06
    DISABLE
    0.06
    Act Density 0.065%

    No Known Activations