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

    Neuronpedia

    INDEX
    Explanations

    blind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mechanics
    -0.07
     Mountains
    -0.06
    前に
    -0.06
    weapon
    -0.06
    الف
    -0.06
    шка
    -0.06
     Нас
    -0.06
     obr
    -0.06
    maları
    -0.06
    Having
    -0.06
    POSITIVE LOGITS
     ترجمه
    0.06
    _CLR
    0.06
    orno
    0.06
    .phi
    0.06
     غذ
    0.06
     спир
    0.06
    ITO
    0.06
    障
    0.06
     Surgical
    0.06
    -strip
    0.06
    Act Density 0.010%

    No Known Activations