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

    Neuronpedia

    INDEX
    Explanations

    Illicit activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deklar
    -0.08
    Merge
    -0.07
    ovie
    -0.07
    ీవ
    -0.07
     enqueue
    -0.07
    -ind
    -0.07
     starke
    -0.07
     strengthens
    -0.07
     bowling
    -0.07
    ീവ
    -0.07
    POSITIVE LOGITS
    สิน
    0.10
     ruthless
    0.09
    waren
    0.09
     Traders
    0.09
    ಗಾರ
    0.09
    ாளர்
    0.08
    wijze
    0.08
     caravan
    0.08
    หุ้น
    0.08
    /access
    0.08
    Act Density 0.017%

    No Known Activations