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

    Neuronpedia

    INDEX
    Explanations

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ইংরেজি
    0.52
     schemes
    0.50
    emote
    0.49
     وظ
    0.49
     schemas
    0.47
     palettes
    0.46
     dhammo
    0.44
     pallets
    0.44
     xo
    0.44
     কণ্
    0.44
    POSITIVE LOGITS
    سبوع
    0.51
    ադ
    0.48
    σιμοποι
    0.48
    骂
    0.47
    ڵ
    0.45
     Fellows
    0.45
    tku
    0.44
    史
    0.44
    роид
    0.43
    ית
    0.43
    Act Density 0.001%

    No Known Activations