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

    Neuronpedia

    INDEX
    Explanations

    css declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     outgoing
    0.42
     gerek
    0.39
     spoiler
    0.39
     jokes
    0.39
     streaks
    0.38
     noise
    0.38
     accesorios
    0.38
     free
    0.37
     lucu
    0.37
     apparatus
    0.37
    POSITIVE LOGITS
    mittag
    0.42
    peria
    0.42
     stood
    0.41
    綺
    0.40
    धि
    0.39
    цаў
    0.39
    ajati
    0.38
    ана
    0.38
    Lunch
    0.38
    𒈬
    0.38
    Act Density 0.020%

    No Known Activations