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

    Neuronpedia

    INDEX
    Explanations

    PDF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thuận
    -0.08
    _TEXTURE
    -0.07
    _sem
    -0.07
    Jeste
    -0.07
    역
    -0.07
     위원
    -0.07
     wind
    -0.07
    _Title
    -0.07
    飞船
    -0.07
     נשמע
    -0.07
    POSITIVE LOGITS
    逼近
    0.07
     lightweight
    0.07
    tlement
    0.07
    uais
    0.07
     SEX
    0.07
    SCALL
    0.06
    至上
    0.06
    潮湿
    0.06
    䓖
    0.06
    管控
    0.06
    Act Density 0.002%

    No Known Activations