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

    Neuronpedia

    INDEX
    Explanations

    smiley faces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.46
    aga
    0.44
    🔥
    0.42
    tableFuture
    0.42
    💥
    0.41
    =(
    0.41
    (!
    0.40
    🥺
    0.40
    amp
    0.39
    ВИ
    0.39
    POSITIVE LOGITS
    菒
    0.44
    seriously
    0.39
     urč
    0.38
     cultura
    0.38
     troubleshoot
    0.38
    ာ
    0.38
     incumb
    0.38
    ىڭ
    0.37
     broaden
    0.37
     setback
    0.37
    Act Density 0.002%

    No Known Activations