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

    Neuronpedia

    INDEX
    Explanations

    my purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    braith
    0.98
    ేక
    0.95
    arguments
    0.95
    logit
    0.92
     traffickers
    0.91
     factorización
    0.91
     hopeless
    0.90
     logika
    0.90
    indak
    0.89
    prefixes
    0.89
    POSITIVE LOGITS
    osphere
    0.83
     Meals
    0.82
     Life
    0.80
     great
    0.78
    жде
    0.78
     night
    0.77
     larger
    0.77
     famous
    0.77
     Sequel
    0.76
     му
    0.76
    Act Density 0.000%

    No Known Activations