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

    Neuronpedia

    INDEX
    Explanations

    compose better music

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     malah
    0.37
     오히려
    0.37
    urra
    0.36
     امرأة
    0.36
    syn
    0.35
     justru
    0.34
     сма
    0.34
     छुटकारा
    0.34
    snow
    0.33
     pulang
    0.33
    POSITIVE LOGITS
    鲞
    0.42
    टीसी
    0.40
     안녕하세요
    0.40
    𝗝
    0.40
     htmlFor
    0.38
    ты
    0.38
     hObject
    0.38
    𝓛
    0.38
    ὢ
    0.37
     чтобы
    0.37
    Act Density 0.583%

    No Known Activations