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

    Neuronpedia

    INDEX
    Explanations

    you choose or use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DISCLAIMED
    0.52
    sendPluginResult
    0.48
     hydrochloric
    0.47
    gespr
    0.47
     разработ
    0.46
    <unused1640>
    0.44
     Borneo
    0.43
     சுண்ணா
    0.43
     Sumatra
    0.42
     полномо
    0.42
    POSITIVE LOGITS
    م
    0.49
    Β
    0.48
     et
    0.45
     de
    0.42
     Component
    0.41
     ή
    0.41
     dell
    0.41
    β
    0.41
     ול
    0.41
     aé
    0.41
    Act Density 0.002%

    No Known Activations