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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RENDER
    -0.06
     rims
    -0.06
    yet
    -0.06
    allows
    -0.06
     assistant
    -0.06
     gritty
    -0.06
    —they
    -0.06
    .account
    -0.06
    Пол
    -0.06
     conduc
    -0.06
    POSITIVE LOGITS
     Kendall
    0.07
    asting
    0.07
     Every
    0.06
    ydro
    0.06
    促
    0.06
    ural
    0.06
    .every
    0.06
    стров
    0.06
    0.06
    ен
    0.06
    Act Density 0.010%

    No Known Activations