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

    Neuronpedia

    INDEX
    Explanations

    * followed by punctuation or "to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     berkembang
    0.53
     청
    0.52
     kişi
    0.52
     ak
    0.51
     τὸν
    0.51
     동물
    0.51
     zawod
    0.50
     ኮ
    0.50
     Público
    0.50
     త
    0.50
    POSITIVE LOGITS
    ারের
    0.54
    sized
    0.48
    呈
    0.48
    ьогодні
    0.45
    dsl
    0.45
    सरण
    0.43
    Staying
    0.43
    df
    0.43
    drag
    0.43
    اندی
    0.43
    Act Density 0.000%

    No Known Activations