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

    Neuronpedia

    INDEX
    Explanations

    iterable and enumerable types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ethe
    0.73
    ਾਈ
    0.68
    ä
    0.67
    ون
    0.66
    killers
    0.65
    اری
    0.63
    ᱓
    0.61
    incorrect
    0.61
    emps
    0.61
     கற்க
    0.59
    POSITIVE LOGITS
     (
    0.75
    0.70
     mixtape
    0.69
     iterable
    0.68
    ة
    0.65
    -
    0.64
    in
    0.63
    ।
    0.62
     SaaS
    0.59
     ge
    0.59
    Act Density 0.001%

    No Known Activations