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

    Neuronpedia

    INDEX
    Explanations

    App function declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ad
    0.70
    ด
    0.61
    ط
    0.61
    ant
    0.59
    ut
    0.59
    en
    0.58
    ur
    0.57
    est
    0.57
    एफ
    0.57
    त
    0.56
    POSITIVE LOGITS
     négy
    0.61
     sinned
    0.56
    ייס
    0.54
     Nucle
    0.52
     is
    0.51
    鑾
    0.50
     கூட்டணிய
    0.50
    uminium
    0.48
    ሮ
    0.48
    ?
    0.48
    Act Density 0.001%

    No Known Activations