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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    車
    -0.09
    Failed
    -0.08
    nd
    -0.08
    msgs
    -0.08
    飞行
    -0.08
     passed
    -0.07
    bin
    -0.07
     downloads
    -0.07
    盾
    -0.07
    نك
    -0.07
    POSITIVE LOGITS
    نحن
    0.08
    แตก
    0.07
    headline
    0.07
     özellikleri
    0.07
     проблемы
    0.07
     yön
    0.07
    𠙶
    0.07
    _HAVE
    0.07
     לפעמים
    0.07
     Coat
    0.07
    Act Density 0.001%

    No Known Activations