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

    Neuronpedia

    INDEX
    Explanations

    listing categories and columns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     धूमधाम
    0.40
     irgende
    0.40
     جت
    0.39
     esattamente
    0.38
     dokładnie
    0.38
     precies
    0.38
     exactamente
    0.38
    fortun
    0.37
    ዱ
    0.36
    attamente
    0.36
    POSITIVE LOGITS
     column
    0.74
    欄
    0.73
     category
    0.72
     listed
    0.71
     row
    0.69
     categories
    0.69
     section
    0.63
     rows
    0.63
     coluna
    0.63
     kolom
    0.63
    Act Density 0.026%

    No Known Activations