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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    чить
    -0.06
     تاریخ
    -0.06
    elsius
    -0.06
    aju
    -0.06
     quarter
    -0.06
    .integer
    -0.06
    likelihood
    -0.06
     grado
    -0.06
     degree
    -0.06
     있는데
    -0.06
    POSITIVE LOGITS
    /${
    0.06
    .skill
    0.06
    .xx
    0.06
    UNC
    0.06
    iffin
    0.06
    Places
    0.06
     Spiritual
    0.06
     느�
    0.06
     lidé
    0.06
     Enforcement
    0.06
    Act Density 0.215%

    No Known Activations