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

    Neuronpedia

    INDEX
    Explanations

    command not found

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     زیرمه
    0.29
    可谓
    0.29
    可以说是
    0.27
    intérieur
    0.26
     Zusätzlich
    0.24
    糈
    0.24
    öder
    0.24
     شرطونه
    0.24
     تړل
    0.24
    䂘
    0.24
    POSITIVE LOGITS
    1
    0.41
    _
    0.33
     and
    0.32
    7
    0.31
    ifying
    0.30
    8
    0.30
     of
    0.28
    imize
    0.28
    ങ്കി
    0.28
    र्जी
    0.27
    Act Density 0.350%

    No Known Activations