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

    Neuronpedia

    INDEX
    Explanations

    technical jargon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    粿
    -0.07
    orris
    -0.07
    ╁
    -0.06
     nostalg
    -0.06
    ukkit
    -0.06
    霸气
    -0.06
    пут
    -0.06
    quirrel
    -0.06
    atie
    -0.06
     Boise
    -0.06
    POSITIVE LOGITS
    _score
    0.09
    잦
    0.07
     govern
    0.07
    _pass
    0.07
     ז
    0.07
    -ab
    0.07
    `}
    0.07
     PHP
    0.07
    作為
    0.07
     ж
    0.07
    Act Density 0.142%

    No Known Activations