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

    Neuronpedia

    INDEX
    Explanations

    Egencia or example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     více
    0.70
     Affirm
    0.67
     ಮಂಗಳ
    0.66
     Baat
    0.66
     Daha
    0.64
     документ
    0.62
     свар
    0.61
     Beding
    0.61
     farmer
    0.60
     Dism
    0.60
    POSITIVE LOGITS
    Runtime
    0.62
    T
    0.62
    Structuring
    0.60
     stare
    0.59
     juist
    0.56
     smack
    0.56
    Translation
    0.55
    Toy
    0.55
    Undo
    0.54
    A
    0.53
    Act Density 0.000%

    No Known Activations