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

    Neuronpedia

    INDEX
    Explanations

    Important cautionary remarks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …
    0.71
    ...
    0.70
     👋
    0.63
    ↵↵
    0.63
    !");
    0.61
    "):
    0.61
     ...
    0.58
    !
    0.57
    Respect
    0.57
    휴
    0.57
    POSITIVE LOGITS
    的には
    1.20
    voorbeeld
    1.08
     inoltre
    1.03
     erste
    1.03
     propuesta
    1.02
     arranque
    1.01
     einzige
    0.98
     gleiche
    0.97
     นี้
    0.96
    としては
    0.95
    Act Density 1.016%

    No Known Activations