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

    Neuronpedia

    INDEX
    Explanations

    HAV

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NELL
    0.39
    няет
    0.38
    PhCH
    0.38
    শের
    0.37
     Tribes
    0.37
    armes
    0.36
     ಅಂ
    0.36
    Giải
    0.35
    하고자
    0.35
    PHEN
    0.35
    POSITIVE LOGITS
    king
    0.39
     ori
    0.39
    ورة
    0.38
     أد
    0.38
     transforma
    0.37
     ensure
    0.36
    uosa
    0.36
     بۇ
    0.36
    ging
    0.36
     King
    0.35
    Act Density 0.000%

    No Known Activations