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

    Neuronpedia

    INDEX
    Explanations

    numbers and mathematical operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pokémon
    1.04
     diligently
    0.89
     Pokemon
    0.88
     antire
    0.86
     conscientious
    0.86
     PvP
    0.85
     OneDrive
    0.85
     overseen
    0.84
     solucionar
    0.84
     assimilation
    0.83
    POSITIVE LOGITS
    9
    2.47
    6
    2.44
    5
    2.43
    8
    2.42
    7
    2.41
    4
    2.41
    3
    2.35
    2
    2.35
    1
    2.19
    ６
    1.68
    Act Density 0.658%

    No Known Activations