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

    Neuronpedia

    INDEX
    Explanations

    Python/Flask code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _lens
    -0.07
     ссыл
    -0.06
     Parl
    -0.06
     Jiří
    -0.06
    ії
    -0.06
     Giovanni
    -0.06
    .agent
    -0.06
     licences
    -0.06
    _shape
    -0.06
    CASCADE
    -0.05
    POSITIVE LOGITS
    거
    0.07
    adb
    0.06
    شر
    0.06
    aded
    0.06
    +".
    0.06
     önce
    0.06
     بهره
    0.06
    맥
    0.06
     허
    0.06
    ICS
    0.06
    Act Density 0.001%

    No Known Activations