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

    Neuronpedia

    INDEX
    Explanations

    small amount or degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     somewhat
    0.48
     quicker
    0.47
     darker
    0.46
     denser
    0.45
     belirli
    0.45
     shorter
    0.45
     quieter
    0.45
    Excess
    0.44
     simpler
    0.43
     faster
    0.42
    POSITIVE LOGITS
     paltry
    1.62
     barely
    1.59
     meagre
    1.55
     meager
    1.52
     pitiful
    1.51
     pathetic
    1.41
     minuscule
    1.31
     hardly
    1.24
     scarcely
    1.23
     feeble
    1.18
    Act Density 0.064%

    No Known Activations