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

    Neuronpedia

    INDEX
    Explanations

    sculpting with brushes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    အတွ
    0.64
     정보를
    0.63
    的样子
    0.61
     божомолу
    0.59
    ಗೊಂಡ
    0.59
     Неза
    0.59
    განიზ
    0.59
     thời
    0.58
     조사
    0.58
     হইতেছিল
    0.58
    POSITIVE LOGITS
    .
    0.78
    Let
    0.64
     .
    0.63
    eln
    0.62
    ب
    0.62
    el
    0.61
     as
    0.61
    k
    0.60
    at
    0.60
    bien
    0.60
    Act Density 0.000%

    No Known Activations