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

    Neuronpedia

    INDEX
    Explanations

    T

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fullfile
    -0.07
    ис
    -0.07
     bursting
    -0.07
    ﺚ
    -0.06
    .IsTrue
    -0.06
     considerations
    -0.06
    Tho
    -0.06
     ");
    -0.06
    ῐ
    -0.06
     Alexis
    -0.06
    POSITIVE LOGITS
     Ravens
    0.08
    혁
    0.07
     Mormons
    0.07
    Kate
    0.07
    Santa
    0.07
     salt
    0.07
     periodic
    0.07
    家电
    0.07
     unbelievable
    0.07
    ולוג
    0.06
    Act Density 0.000%

    No Known Activations