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

    Neuronpedia

    INDEX
    Explanations

    phrases following certain tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্রিয়া
    0.44
    iling
    0.43
    ure
    0.42
    ile
    0.42
     superiore
    0.41
     vain
    0.41
    ille
    0.39
     you
    0.39
    ",
    0.39
     come
    0.39
    POSITIVE LOGITS
    Bearing
    0.38
     بأ
    0.37
     బాగా
    0.36
    ੀ
    0.36
    ненко
    0.36
    さまざ
    0.35
    ి
    0.35
     ಹೊ
    0.35
    Brainz
    0.35
    缑
    0.35
    Act Density 0.000%

    No Known Activations