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

    Neuronpedia

    INDEX
    Explanations

    settings, query, path, wizard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нг
    1.51
     inmediata
    1.38
    ming
    1.27
     importants
    1.27
    ണ
    1.25
     asesin
    1.22
    adayo
    1.20
     Гру
    1.20
    ンの
    1.18
    นั้น
    1.18
    POSITIVE LOGITS
     einzelne
    1.30
     whatnot
    1.22
    gerät
    1.20
    akses
    1.19
    家居
    1.11
    と考えられる
    1.11
    irm
    1.09
     toán
    1.09
    çok
    1.09
     começa
    1.09
    Act Density 0.001%

    No Known Activations