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

    Neuronpedia

    INDEX
    Explanations

    speedrunning, pressure, browning, got

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    owment
    0.42
     hvert
    0.42
     হওয়ার
    0.40
    )\|_{\
    0.39
     Accesat
    0.38
    मर्श
    0.37
     Prado
    0.37
    nlm
    0.36
    FragmentManager
    0.36
    BindView
    0.36
    POSITIVE LOGITS
     ин
    0.44
     beet
    0.44
    <unused74>
    0.40
    सेस
    0.38
    纸
    0.37
    ാപാ
    0.37
    駕
    0.35
    ज्ञ
    0.35
    зон
    0.35
     אי
    0.34
    Act Density 0.000%

    No Known Activations