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

    Neuronpedia

    INDEX
    Explanations

    explanation of being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    newblock
    0.44
    textView
    0.42
    ారం
    0.40
     Stel
    0.40
     inne
    0.40
    তুন
    0.39
     hemorrhage
    0.39
    इनस
    0.38
     ناقص
    0.38
    音
    0.38
    POSITIVE LOGITS
    ian
    0.52
    rand
    0.51
    도
    0.48
     __
    0.47
    🇩
    0.47
    야
    0.46
    ak
    0.45
     rand
    0.45
    іо
    0.45
    ulang
    0.45
    Act Density 0.000%

    No Known Activations