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

    Neuronpedia

    INDEX
    Explanations

    desktop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (subject
    -0.06
     liste
    -0.06
     haber
    -0.06
    _program
    -0.06
     asteroid
    -0.06
     soud
    -0.06
    /am
    -0.06
    컴
    -0.06
     Syrian
    -0.06
    (stats
    -0.06
    POSITIVE LOGITS
    )->
    0.07
    odus
    0.07
    decimal
    0.06
    accuracy
    0.06
    Spark
    0.06
     پنج
    0.06
    tainment
    0.06
    шив
    0.06
    し
    0.06
    laması
    0.06
    Act Density 0.003%

    No Known Activations