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

    Neuronpedia

    INDEX
    Explanations

    categories and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kn
    0.40
    ognito
    0.38
     workout
    0.36
    aster
    0.36
    qual
    0.35
    িকল্প
    0.35
     esport
    0.35
     Emotions
    0.35
    ence
    0.35
     formulas
    0.35
    POSITIVE LOGITS
    नैतिक
    0.44
    㖦
    0.41
    晎
    0.40
    桻
    0.40
     höhere
    0.39
     مرف
    0.39
    㚣
    0.39
     RBS
    0.39
    䅡
    0.38
     चुके
    0.38
    Act Density 0.000%

    No Known Activations