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

    Neuronpedia

    INDEX
    Explanations

    remember figure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tortoise
    0.42
     resolutions
    0.41
    ாக்க
    0.41
    ானி
    0.41
     module
    0.39
     rewritten
    0.39
    ($
    0.38
     puffs
    0.38
     Resolutions
    0.38
     crisp
    0.38
    POSITIVE LOGITS
     Antonia
    0.41
     Альбер
    0.41
     पूर्वानुमान
    0.39
    턱
    0.39
    physiological
    0.38
    꿰
    0.38
    bedingungen
    0.38
     Francesca
    0.38
     Abbot
    0.38
     Віль
    0.38
    Act Density 0.000%

    No Known Activations