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

    Neuronpedia

    INDEX
    Explanations

    following technical phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    не
    0.82
    пол
    0.80
    ओं
    0.70
     TSS
    0.68
    но
    0.68
     acum
    0.68
     тех
    0.67
    дено
    0.66
    це
    0.65
    ду
    0.65
    POSITIVE LOGITS
    utives
    0.78
    olojik
    0.78
    秸
    0.78
    withstanding
    0.78
    kaç
    0.77
     pamoja
    0.77
    ούς
    0.76
     धारा
    0.75
    atively
    0.75
    skiej
    0.75
    Act Density 0.001%

    No Known Activations