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

    Neuronpedia

    INDEX
    Explanations

    This will be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vaisse
    0.52
    Pair
    0.50
    akkh
    0.47
    órmula
    0.46
    ueve
    0.45
    phyll
    0.45
    ताव
    0.44
    Giov
    0.44
    搛
    0.44
    áver
    0.44
    POSITIVE LOGITS
     wę
    0.45
     история
    0.45
     prix
    0.45
     restaurants
    0.44
    際
    0.44
     practical
    0.44
     juicy
    0.43
     history
    0.43
    रेख
    0.43
     analogues
    0.42
    Act Density 0.001%

    No Known Activations