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

    Neuronpedia

    INDEX
    Explanations

    not uncommon, from recommending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     పని
    0.47
    alık
    0.46
    impanan
    0.45
    श्व
    0.43
    قي
    0.43
    蚜
    0.43
    ुर
    0.42
    ਾਂ
    0.42
     Beads
    0.42
    श्रेष्ठ
    0.42
    POSITIVE LOGITS
     diven
    0.46
    ---
    0.43
     sott
    0.42
     breve
    0.42
     ztr
    0.42
     who
    0.42
     zask
    0.41
     quella
    0.41
     smrt
    0.41
    元
    0.41
    Act Density 0.009%

    No Known Activations