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

    Neuronpedia

    INDEX
    Explanations

    posit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prime
    -0.07
    fila
    -0.07
     Пра
    -0.06
    '].'"
    -0.06
    dirs
    -0.06
    diği
    -0.06
    yclerview
    -0.06
    ('*',
    -0.06
     hầu
    -0.06
     تنها
    -0.06
    POSITIVE LOGITS
     posit
    0.29
    posit
    0.11
    POSIT
    0.07
     Fang
    0.07
     sat
    0.07
     spiel
    0.06
    ationale
    0.06
     pozit
    0.06
    opal
    0.06
    rapy
    0.06
    Act Density 0.001%

    No Known Activations