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

    Neuronpedia

    INDEX
    Explanations

    Errors and corruption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /full
    -0.07
    52
    -0.06
     marty
    -0.06
     Sup
    -0.06
     SX
    -0.06
     Civ
    -0.06
     GBP
    -0.06
     ワ
    -0.06
     released
    -0.06
    							
↵
    -0.06
    POSITIVE LOGITS
     enthusiastic
    0.07
    erais
    0.07
    __,↵
    0.07
    :::::|
    0.07
    -ver
    0.06
    ذه
    0.06
    .verify
    0.06
    callable
    0.06
    Province
    0.06
    _arm
    0.06
    Act Density 0.015%

    No Known Activations