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

    Neuronpedia

    INDEX
    Explanations

    CEO, seeking, researches, multilingual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     바탕
    0.59
     subjug
    0.53
     predecessors
    0.51
     사이
    0.50
     쌍
    0.50
     argumentative
    0.49
     anisotropic
    0.48
     chat
    0.48
     claws
    0.48
     불구하고
    0.48
    POSITIVE LOGITS
    o
    0.66
    r
    0.65
    s
    0.64
    en
    0.63
    ar
    0.62
    <0x80>
    0.60
    ه
    0.56
    布
    0.54
    a
    0.52
    ，
    0.52
    Act Density 0.000%

    No Known Activations