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

    Neuronpedia

    INDEX
    Explanations

    time formats and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     предпо
    0.45
    assets
    0.43
    b
    0.42
    asets
    0.42
    darwin
    0.42
    ki
    0.41
    natal
    0.41
    dgs
    0.41
    expressions
    0.41
    avatar
    0.41
    POSITIVE LOGITS
     solaire
    0.50
     privy
    0.48
     ciel
    0.48
     cub
    0.47
     acert
    0.47
     tiem
    0.46
     wynik
    0.46
     graça
    0.46
     dedu
    0.46
     limites
    0.46
    Act Density 0.006%

    No Known Activations