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

    Neuronpedia

    INDEX
    Explanations

    refinement, refactoring, referencing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    même
    0.92
    IS
    0.90
    appendText
    0.90
     saman
    0.88
    я
    0.87
    Cecil
    0.85
     lingua
    0.85
    ificato
    0.85
    ди
    0.85
    ých
    0.83
    POSITIVE LOGITS
    actoring
    1.09
    erees
    1.08
    ugio
    1.04
     recrystall
    1.04
    丆
    1.04
    utable
    1.01
    lected
    1.01
    RESH
    0.99
     саны
    0.99
    utations
    0.96
    Act Density 0.075%

    No Known Activations