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

    Neuronpedia

    INDEX
    Explanations

    specific quantifiers and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pada
    0.51
     esfuer
    0.49
    También
    0.47
     publiée
    0.47
     esclus
    0.45
    formerly
    0.44
    Según
    0.44
    ে
    0.44
    Pour
    0.44
    ফি
    0.43
    POSITIVE LOGITS
    ោ
    0.44
    iffel
    0.44
     disrupt
    0.43
     đáo
    0.42
    ῳ
    0.41
    otics
    0.41
     Louvre
    0.41
    وات
    0.40
    pson
    0.39
     الذي
    0.39
    Act Density 0.000%

    No Known Activations