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

    Neuronpedia

    INDEX
    Explanations

    Engine Architecture, Paid, music, book, Tab, liter, scent, Architect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ifiées
    0.46
    IMATE
    0.45
    િ
    0.45
    हट
    0.45
    ភ្
    0.44
    cket
    0.44
     destacados
    0.43
    鿆
    0.42
     remind
    0.41
    External
    0.41
    POSITIVE LOGITS
    scattering
    0.45
    splitting
    0.45
     Correlation
    0.44
     Divide
    0.41
    sleeping
    0.40
    relation
    0.40
    theoretic
    0.40
     awning
    0.40
     coarsely
    0.40
    characterized
    0.40
    Act Density 0.003%

    No Known Activations