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

    Neuronpedia

    INDEX
    Explanations

    Figures and diagrams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ساخت
    -0.07
     이루
    -0.06
    �
    -0.06
    _Num
    -0.06
    WATCH
    -0.06
     DPS
    -0.06
    嘛
    -0.06
    _cov
    -0.06
    matplotlib
    -0.06
    -watch
    -0.06
    POSITIVE LOGITS
     трав
    0.07
    elan
    0.07
     Uploaded
    0.07
     yemek
    0.06
     Lê
    0.06
    řel
    0.06
     […
    0.06
    یست
    0.06
    操作
    0.06
     produced
    0.06
    Act Density 0.013%

    No Known Activations