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

    Neuronpedia

    INDEX
    Explanations

    explaining why or hashing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Diane
    0.46
     pis
    0.45
     arrivée
    0.45
     Rankin
    0.45
     Edith
    0.44
     dimensi
    0.44
     choć
    0.43
     தினத்தன்று
    0.43
     Armand
    0.43
     dimens
    0.42
    POSITIVE LOGITS
    ")
    0.44
    ama
    0.42
    तो
    0.42
    tokenizer
    0.42
    they
    0.41
    test
    0.41
    !}{
    0.41
    town
    0.40
    scattering
    0.40
    then
    0.40
    Act Density 0.001%

    No Known Activations