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

    Neuronpedia

    INDEX
    Explanations

    nothing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    某个
    0.45
    某一
    0.36
     एखाद्या
    0.36
    ликт
    0.36
     algum
    0.35
    BRUARY
    0.33
    etapkan
    0.33
     кандай
    0.33
    ỏ
    0.33
    某种
    0.33
    POSITIVE LOGITS
     nothing
    4.38
    nothing
    3.92
     Nothing
    3.88
    Nothing
    3.80
     NOTHING
    3.63
     nada
    3.47
     ничего
    3.44
     nichts
    3.25
     rien
    3.11
     nimic
    2.97
    Act Density 0.091%

    No Known Activations