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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olver
    -0.07
    jong
    -0.07
     JDK
    -0.07
    🇵
    -0.07
    纪
    -0.07
     hydrogen
    -0.06
    景德
    -0.06
    .DateTimePicker
    -0.06
    -K
    -0.06
    ichen
    -0.06
    POSITIVE LOGITS
    强调
    0.07
    饲料
    0.07
     эта
    0.07
     referring
    0.07
     eats
    0.07
    吟
    0.07
     graffiti
    0.07
    完整
    0.07
     объявл
    0.07
    itness
    0.06
    Act Density 0.067%

    No Known Activations