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

    Neuronpedia

    INDEX
    Explanations

    Canis lupus familiaris

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hacking
    0.42
     pain
    0.39
     marrow
    0.38
    okol
    0.36
     outliers
    0.36
    खेल
    0.36
     hacked
    0.36
     quenched
    0.36
    tipped
    0.36
    unlock
    0.35
    POSITIVE LOGITS
     строка
    0.41
     അല്ലെങ്കിൽ
    0.40
     thấy
    0.38
     graphic
    0.38
     থেমে
    0.38
     н
    0.35
     ببین
    0.35
     Graphic
    0.35
    见
    0.35
    见到
    0.34
    Act Density 0.001%

    No Known Activations