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

    Neuronpedia

    INDEX
    Explanations

    AI cannot feel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    covering
    0.44
    Mini
    0.41
    OLF
    0.38
    Shelf
    0.38
    ahir
    0.38
    cover
    0.37
    Distance
    0.37
    winter
    0.37
    详
    0.37
    止
    0.36
    POSITIVE LOGITS
     نیوز
    0.42
     waging
    0.40
    ïdes
    0.40
     hydrolyzed
    0.39
     políticas
    0.38
     replying
    0.38
    esecuzione
    0.38
     attacked
    0.38
    ക്രമ
    0.38
    -{\
    0.37
    Act Density 0.000%

    No Known Activations