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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     daylight
    -0.07
     faithful
    -0.07
    버전
    -0.07
     dorm
    -0.07
    منی
    -0.07
     humili
    -0.06
     него
    -0.06
    Њ
    -0.06
     relaxation
    -0.06
     debris
    -0.06
    POSITIVE LOGITS
     Tel
    0.06
    リカ
    0.06
     Mitt
    0.06
    寶
    0.06
    proxy
    0.06
    丝
    0.06
    #######↵
    0.06
    /Auth
    0.06
    614
    0.06
    _InitStructure
    0.06
    Act Density 0.075%

    No Known Activations