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

    Neuronpedia

    INDEX
    Explanations

    prefixes forming significant words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ቨ
    0.40
    OLOGIA
    0.36
    ईआरटी
    0.34
    Ḍ
    0.34
    PlayerData
    0.34
    QTTR
    0.33
    MktCap
    0.33
    Celula
    0.33
     కానీ
    0.33
    ävät
    0.33
    POSITIVE LOGITS
    oretically
    0.47
    us
    0.36
    is
    0.35
    ing
    0.33
    wood
    0.30
    water
    0.30
    es
    0.29
     oil
    0.29
     Care
    0.29
    text
    0.29
    Act Density 0.148%

    No Known Activations