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

    Neuronpedia

    INDEX
    Explanations

    technical programming and data formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    তুল
    0.45
     Wonders
    0.42
     येतो
    0.42
     materially
    0.40
    रूप
    0.40
    务
    0.40
     स्मार्ट
    0.40
    landı
    0.40
     fichiers
    0.38
    nosi
    0.38
    POSITIVE LOGITS
    ActionMode
    0.41
     plethora
    0.39
     cardinality
    0.35
     Woh
    0.35
     ts
    0.35
    iming
    0.35
     oft
    0.34
     bulb
    0.34
    мии
    0.34
     monastic
    0.33
    Act Density 0.000%

    No Known Activations