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

    Neuronpedia

    INDEX
    Explanations

    facing challenges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    虓
    -0.07
     fas
    -0.07
     leth
    -0.07
    ivor
    -0.07
     شب
    -0.06
    gulp
    -0.06
     parts
    -0.06
    ₤
    -0.06
    .addEventListener
    -0.06
    alfa
    -0.06
    POSITIVE LOGITS
    浮现
    0.08
    &M
    0.08
     Rot
    0.07
    мысл
    0.07
     Rut
    0.07
    录
    0.07
     NATIONAL
    0.07
     w
    0.07
     التن
    0.07
    _reference
    0.07
    Act Density 0.009%

    No Known Activations