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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gus
    -0.08
     thủy
    -0.07
    他们都
    -0.07
    .spy
    -0.07
    .insert
    -0.07
    女兒
    -0.07
    <dim
    -0.07
    (('
    -0.07
    ґ
    -0.07
    尽可能
    -0.07
    POSITIVE LOGITS
    corn
    0.08
    (Level
    0.07
     Hemisphere
    0.07
     леч
    0.07
    Much
    0.07
    מוק
    0.07
    مساب
    0.07
     Prop
    0.06
     Mile
    0.06
     Московск
    0.06
    Act Density 0.084%

    No Known Activations