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

    Neuronpedia

    INDEX
    Explanations

    creating outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     some
    1.07
     niektor
    0.89
     how
    0.82
     κάπο
    0.79
     SOME
    0.78
    some
    0.78
     you
    0.75
     marketers
    0.75
     சிலர்
    0.74
     Some
    0.74
    POSITIVE LOGITS
     headwinds
    0.91
     температур
    0.86
     خواہش
    0.86
     wedstrij
    0.85
     యుద్ధ
    0.83
    awareness
    0.83
    érences
    0.83
    dependencies
    0.81
    事實
    0.81
     известных
    0.80
    Act Density 0.087%

    No Known Activations