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

    Neuronpedia

    INDEX
    Explanations

    yes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    다
    1.35
    )}$,
    1.22
    VENTION
    1.13
    jected
    1.12
     smelled
    1.11
     Règles
    1.10
    вими
    1.06
    EST
    1.05
    THE
    1.05
     allait
    1.04
    POSITIVE LOGITS
    ين
    1.90
    ів
    1.42
    l
    1.39
    ை
    1.39
    ം
    1.38
    il
    1.38
    स
    1.34
    い
    1.32
    ید
    1.31
    िया
    1.30
    Act Density 0.093%

    No Known Activations