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

    Neuronpedia

    INDEX
    Explanations

    brackets before pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    딤
    -0.08
     نسبة
    -0.07
    ux
    -0.07
    밖에
    -0.07
    (samples
    -0.07
    ʣ
    -0.07
     תו
    -0.06
     wrapping
    -0.06
     Sche
    -0.06
     rods
    -0.06
    POSITIVE LOGITS
    تظ
    0.09
    Detroit
    0.07
    Miami
    0.07
     אית
    0.07
    연
    0.07
    olkata
    0.07
    ultimo
    0.07
     pricey
    0.07
    Rachel
    0.07
    Evento
    0.06
    Act Density 0.003%

    No Known Activations