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

    Neuronpedia

    INDEX
    Explanations

    allowed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     camino
    -0.07
     цьому
    -0.07
     никогда
    -0.07
    一緒
    -0.07
    _rename
    -0.06
    -category
    -0.06
     Spor
    -0.06
    频
    -0.06
    .Di
    -0.06
     nø
    -0.06
    POSITIVE LOGITS
    aac
    0.07
    IG
    0.07
    caff
    0.07
     convenience
    0.06
    abric
    0.06
     복
    0.06
    音乐
    0.06
    生物
    0.06
    таки
    0.06
    (foo
    0.06
    Act Density 0.006%

    No Known Activations