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

    Neuronpedia

    INDEX
    Explanations

    spectro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     architekt
    -0.07
     Ta
    -0.07
    lags
    -0.07
    室
    -0.06
    ö
    -0.06
    ysterious
    -0.06
    (argv
    -0.06
     dimin
    -0.06
    ห
    -0.06
    恩
    -0.06
    POSITIVE LOGITS
    系统
    0.07
    :'.$
    0.07
     venture
    0.07
    ">
    0.07
    रल
    0.06
    ystate
    0.06
    antages
    0.06
    _loading
    0.06
     replacements
    0.06
     flavors
    0.06
    Act Density 0.010%

    No Known Activations