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

    Neuronpedia

    INDEX
    Explanations

    optimize, best solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     correto
    0.49
    ।
    0.48
    ματος
    0.48
     escrita
    0.47
     químicos
    0.46
     contenido
    0.46
     रचना
    0.46
    ﻭ
    0.46
     ।
    0.46
     कहा
    0.46
    POSITIVE LOGITS
    wide
    0.40
    集中
    0.40
     manoeuv
    0.39
     cooperation
    0.39
     konzent
    0.39
     manoeuvre
    0.39
     همکاری
    0.39
    ماع
    0.39
    ′-
    0.38
     வழியாக
    0.38
    Act Density 0.001%

    No Known Activations