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

    Neuronpedia

    INDEX
    Explanations

    punctuation and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itioner
    -0.08
     expressly
    -0.07
    δώ
    -0.07
     phủ
    -0.07
    RESSION
    -0.06
     اق
    -0.06
    visions
    -0.06
    _signals
    -0.06
    CTOR
    -0.06
    ISK
    -0.06
    POSITIVE LOGITS
    heure
    0.07
     conquer
    0.06
    'aut
    0.06
     vegetarian
    0.06
     Hiç
    0.06
     Bě
    0.06
    ош
    0.06
    Present
    0.06
    <Student
    0.06
    (coeff
    0.06
    Act Density 0.087%

    No Known Activations