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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -example
    -0.08
    مسرح
    -0.07
    瞑
    -0.07
     slapped
    -0.07
    装卸
    -0.06
    农业生产
    -0.06
     Verfügung
    -0.06
     terminating
    -0.06
     RELEASE
    -0.06
    簪
    -0.06
    POSITIVE LOGITS
    害羞
    0.08
    _eth
    0.07
     shades
    0.07
     fileInfo
    0.06
    瑨
    0.06
    쪘
    0.06
     Elli
    0.06
    昣
    0.06
    ynth
    0.06
    有没有
    0.06
    Act Density 0.016%

    No Known Activations