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

    Neuronpedia

    INDEX
    Explanations

    actions or descriptors after commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.53
     or
    0.48
    ’
    0.44
     maupun
    0.44
    ik
    0.44
     หรือ
    0.44
     ឬ
    0.44
     alebo
    0.42
     algebras
    0.42
    ellers
    0.41
    POSITIVE LOGITS
    with
    0.39
     be
    0.36
    กับ
    0.35
    是
    0.34
    يت
    0.33
    고
    0.32
    يس
    0.32
    面向
    0.31
    ｛
    0.31
    исто
    0.31
    Act Density 0.000%

    No Known Activations