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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     کنم
    -0.06
     pill
    -0.06
     ры
    -0.06
     если
    -0.06
    hg
    -0.06
     ملی
    -0.06
    žitě
    -0.06
    .if
    -0.06
     conceive
    -0.06
    .coord
    -0.06
    POSITIVE LOGITS
    CHAN
    0.06
    	constexpr
    0.06
    -party
    0.06
    ")(
    0.06
     disciplinary
    0.06
    utex
    0.06
    InstantiationException
    0.06
    frag
    0.06
    mae
    0.06
    substr
    0.06
    Act Density 0.019%

    No Known Activations