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

    Neuronpedia

    INDEX
    Explanations

    punished for theft; function; Order of component; Forever Alone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ি
    0.93
    ल
    0.90
    ী
    0.83
     dahulu
    0.81
    ist
    0.78
     Smell
    0.78
    venido
    0.76
     路
    0.76
    actic
    0.75
    iphone
    0.75
    POSITIVE LOGITS
    تن
    1.26
    ю
    0.95
     tasse
    0.93
    ప
    0.86
    ے
    0.82
    ны
    0.82
    ään
    0.82
    تان
    0.80
    τα
    0.79
     intents
    0.77
    Act Density 0.000%

    No Known Activations