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

    Neuronpedia

    INDEX
    Explanations

    federally funded research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hunk
    0.57
     minds
    0.52
     sluggish
    0.52
     than
    0.50
     stuffed
    0.50
     burner
    0.50
     flimsy
    0.50
     diligently
    0.49
     spurt
    0.49
     sangu
    0.49
    POSITIVE LOGITS
     сообщения
    0.51
     سپور
    0.49
    ग
    0.48
    ancell
    0.47
     общения
    0.47
    rda
    0.45
    ரு
    0.45
     desped
    0.45
    제목
    0.45
    ना
    0.44
    Act Density 0.000%

    No Known Activations