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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    丏
    -0.07
    imento
    -0.07
    "".
    -0.07
     oleh
    -0.07
    lescope
    -0.07
    _pdu
    -0.06
    .sender
    -0.06
    .signup
    -0.06
    _po
    -0.06
    培
    -0.06
    POSITIVE LOGITS
    atts
    0.07
     Rash
    0.07
    арат
    0.07
    膜
    0.07
    Ⲡ
    0.07
    ㇼ
    0.07
    賦
    0.07
    👻
    0.06
    กว
    0.06
     클
    0.06
    Act Density 0.004%

    No Known Activations