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

    Neuronpedia

    INDEX
    Explanations

    progresses, grows, or matures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Has
    0.73
    significant
    0.73
     needn
    0.71
    Don
    0.69
    是可以
    0.69
    DON
    0.69
     אפ
    0.68
     иметь
    0.67
     HAS
    0.65
     exclamation
    0.65
    POSITIVE LOGITS
     progresses
    1.79
     matures
    1.38
     evolves
    1.35
     unfolds
    1.34
     prepares
    1.27
     nears
    1.24
     progressed
    1.23
     grows
    1.18
     becomes
    1.17
     deepen
    1.16
    Act Density 0.047%

    No Known Activations