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

    Neuronpedia

    INDEX
    Explanations

    mention key details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سؤال
    0.81
     स्क्वायर
    0.80
     nine
    0.79
     Nine
    0.78
     அரசியல்
    0.78
     nueve
    0.76
     రాజకీయ
    0.74
    ===============
    0.73
    Nine
    0.71
    ഞ്ഞ
    0.71
    POSITIVE LOGITS
     favorites
    0.81
     Favor
    0.68
     favorito
    0.67
     favoritos
    0.66
     favoring
    0.65
     key
    0.65
     Key
    0.64
    key
    0.62
     favor
    0.61
    Key
    0.61
    Act Density 0.131%

    No Known Activations