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

    Neuronpedia

    INDEX
    Explanations

    Numerical rankings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itself
    -0.07
    (const
    -0.07
     guaranteed
    -0.07
    DefaultValue
    -0.07
     structures
    -0.07
    _cb
    -0.07
     ctrl
    -0.06
    CTest
    -0.06
     chiều
    -0.06
    _g
    -0.06
    POSITIVE LOGITS
    ompiler
    0.07
    ифика
    0.07
     Learned
    0.07
    钤
    0.07
    פתיחת
    0.06
     bağlı
    0.06
     disb
    0.06
    蓣
    0.06
     Dag
    0.06
    箦
    0.06
    Act Density 0.019%

    No Known Activations