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

    Neuronpedia

    INDEX
    Explanations

    license agreements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pections
    -0.07
    ('|
    -0.07
    宗
    -0.06
    .Guna
    -0.06
    Border
    -0.06
    алеж
    -0.06
    .metro
    -0.06
    ığı
    -0.06
    )`↵
    -0.06
    参加
    -0.06
    POSITIVE LOGITS
     intervened
    0.06
     offenders
    0.06
    _insert
    0.06
     neur
    0.06
     Bravo
    0.06
    ША
    0.06
    knowledge
    0.06
     मन
    0.06
     alan
    0.06
     गय
    0.06
    Act Density 0.008%

    No Known Activations