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

    Neuronpedia

    INDEX
    Explanations

    equal signs, definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     イ
    -0.07
    "]:
    -0.07
    Vin
    -0.07
     Pan
    -0.07
    ipple
    -0.07
    both
    -0.06
     INT
    -0.06
    鏡
    -0.06
     Components
    -0.06
    Span
    -0.06
    POSITIVE LOGITS
     брос
    0.06
    出した
    0.06
     balık
    0.06
     적
    0.06
     šť
    0.06
    Serializable
    0.06
     زندگی
    0.06
     malignant
    0.06
    _fa
    0.06
     профессиональ
    0.06
    Act Density 0.056%

    No Known Activations