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

    Neuronpedia

    INDEX
    Explanations

    root of n

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     காட்சிகள்
    0.48
    OGO
    0.46
     Некоторые
    0.46
    eces
    0.46
     रोचक
    0.45
     Milford
    0.45
     पादु
    0.45
     дальнейшем
    0.45
     завое
    0.44
    goài
    0.44
    POSITIVE LOGITS
     unchanging
    0.44
     cumpr
    0.42
    不需要
    0.41
     computer
    0.40
     cumple
    0.40
     ejército
    0.40
     capacity
    0.39
    褪
    0.39
    tol
    0.39
     sicuramente
    0.39
    Act Density 0.003%

    No Known Activations