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

    Neuronpedia

    INDEX
    Explanations

    names of places and geographical features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ід
    0.64
     sécrétion
    0.59
     fécond
    0.57
    ﻥ
    0.57
    ATING
    0.55
     అంశ
    0.53
    ята
    0.53
     ಅಂಶ
    0.53
     lezione
    0.52
    ﺭ
    0.51
    POSITIVE LOGITS
    ong
    0.77
     for
    0.65
    on
    0.63
    س
    0.59
    ol
    0.59
     to
    0.58
    ik
    0.58
    är
    0.57
     del
    0.55
    ě
    0.50
    Act Density 0.144%

    No Known Activations