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

    Neuronpedia

    INDEX
    Explanations

    competency assessment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.51
     iterations
    0.46
     fra
    0.44
     .
    0.44
    фия
    0.44
     hy
    0.43
     màn
    0.43
     on
    0.42
    ció
    0.41
    Tovar
    0.41
    POSITIVE LOGITS
    퐁
    0.49
    ంట్
    0.47
    उदाहरण
    0.47
    밖
    0.47
     INCLUDING
    0.46
    circular
    0.46
    プリング
    0.46
     wykony
    0.45
    ᔾ
    0.44
    Static
    0.43
    Act Density 0.000%

    No Known Activations