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

    Neuronpedia

    INDEX
    Explanations

    L= or ChadGPT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.55
    s
    0.45
    í
    0.45
    నూ
    0.39
    se
    0.36
    ses
    0.36
    speople
    0.36
    ्य
    0.35
    A
    0.35
    ból
    0.35
    POSITIVE LOGITS
     в
    0.45
     في
    0.43
     alebo
    0.40
    জ
    0.39
     in
    0.39
     eiusmod
    0.39
     digamos
    0.39
     diciamo
    0.38
     cinq
    0.38
     crece
    0.38
    Act Density 2.462%

    No Known Activations