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

    Neuronpedia

    INDEX
    Explanations

    cities, mechanics, MVP, network, fibers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दी
    0.43
    locationX
    0.42
    နယ်
    0.41
     evaporating
    0.41
    oz
    0.41
    sized
    0.41
    வது
    0.40
    IDENTAL
    0.40
    стати
    0.40
    picked
    0.40
    POSITIVE LOGITS
    Baca
    0.53
    je
    0.50
    Hav
    0.50
    Hol
    0.49
    Leia
    0.49
    Teste
    0.46
    Ar
    0.45
    Ke
    0.45
     Lauf
    0.45
    jen
    0.45
    Act Density 0.001%

    No Known Activations