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

    Neuronpedia

    INDEX
    Explanations

    population statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     treatments
    -0.07
     spotlight
    -0.07
    -books
    -0.07
     Romanian
    -0.07
     sw
    -0.06
    high
    -0.06
     pareja
    -0.06
    領
    -0.06
    Someone
    -0.06
    aki
    -0.06
    POSITIVE LOGITS
     válido
    0.06
     strtok
    0.06
    _SERVICE
    0.06
     ΣΤ
    0.06
     MEDIATEK
    0.06
    ：</
    0.06
     Laur
    0.06
    ــــ
    0.06
     calam
    0.06
     کردند
    0.05
    Act Density 0.005%

    No Known Activations