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

    Neuronpedia

    INDEX
    Explanations

    `val` or `data` attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     શકાય
    0.93
     الور
    0.89
     পরবর্ত
    0.88
    proximity
    0.88
     obscurity
    0.88
     calyce
    0.87
     nCount
    0.85
    니아
    0.83
     Pelicans
    0.83
     صہیونی
    0.82
    POSITIVE LOGITS
    en
    1.06
    യുള്ള
    1.01
    l
    0.94
    el
    0.91
     lacking
    0.88
    دف
    0.88
    s
    0.87
    को
    0.85
    aa
    0.84
    ез
    0.84
    Act Density 0.000%

    No Known Activations