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

    Neuronpedia

    INDEX
    Explanations

    looping with indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     |\
    0.78
     |.
    0.77
     🙏
    0.77
     =
    0.74
    Lem
    0.73
    ().
    0.72
     xD
    0.72
     Stein
    0.70
     merino
    0.69
     Prez
    0.69
    POSITIVE LOGITS
     garrison
    0.63
    めた
    0.61
    γά
    0.61
    的位置
    0.60
    がない
    0.60
    探し
    0.59
     мотор
    0.59
    ントン
    0.58
     kanya
    0.58
     aussch
    0.58
    Act Density 0.088%

    No Known Activations