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

    Neuronpedia

    INDEX
    Explanations

    Dataframe code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     נדרש
    -0.07
    _DI
    -0.07
    ㅂ
    -0.07
     pathname
    -0.07
     ipAddress
    -0.07
    usercontent
    -0.06
    .atan
    -0.06
    ᄂ
    -0.06
    ../../../../
    -0.06
    qm
    -0.06
    POSITIVE LOGITS
    Reset
    0.08
     Nicolas
    0.07
    製作
    0.07
    =torch
    0.07
    回复
    0.07
     cloak
    0.06
    讲师
    0.06
     lending
    0.06
    פיר
    0.06
     luật
    0.06
    Act Density 0.101%

    No Known Activations