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

    Neuronpedia

    INDEX
    Explanations

    Writing/text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Д
    -0.07
     chosen
    -0.07
    RAR
    -0.07
    데
    -0.07
     برخی
    -0.07
    imeType
    -0.07
    awner
    -0.06
    ูงส
    -0.06
     tük
    -0.06
    нож
    -0.06
    POSITIVE LOGITS
    忘
    0.07
     Malone
    0.07
    واج
    0.06
     تصویر
    0.06
     driveway
    0.06
    sandbox
    0.06
    _range
    0.06
     fatalError
    0.06
    .“
    0.06
     #↵
    0.06
    Act Density 0.000%

    No Known Activations