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

    Neuronpedia

    INDEX
    Explanations

    path or your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ead
    0.73
     pouquinho
    0.71
    ે
    0.71
    ept
    0.68
    e
    0.68
    o
    0.68
    hos
    0.67
    тий
    0.67
    grams
    0.65
    indx
    0.65
    POSITIVE LOGITS
    㢄
    0.77
    ῆς
    0.76
     buttery
    0.75
     ہد
    0.75
     dxc
    0.73
     Begin
    0.72
     Saviour
    0.72
     Đo
    0.72
     Soleil
    0.71
    েশনে
    0.71
    Act Density 0.015%

    No Known Activations