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

    Neuronpedia

    INDEX
    Explanations

    constantly swirling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     specify
    1.17
     specifies
    1.15
     defaulted
    1.12
     Cedex
    1.11
     selector
    1.09
     disallowed
    1.06
     incorrectly
    1.05
    }|$
    1.03
    蛎
    1.02
    ',\
    1.02
    POSITIVE LOGITS
    And
    1.55
    He
    1.48
    Together
    1.47
    They
    1.46
    It
    1.45
    return
    1.43
     And
    1.43
     humility
    1.40
    ever
    1.40
     communautés
    1.37
    Act Density 0.276%

    No Known Activations