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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    aco
    -0.06
    /pm
    -0.06
     Liberals
    -0.06
     newcomers
    -0.06
    	short
    -0.06
     Mits
    -0.06
    -middle
    -0.06
     blasph
    -0.06
    .FloatField
    -0.06
    POSITIVE LOGITS
    ैम
    0.07
    ']),
    0.06
    _sale
    0.06
     assumption
    0.06
    (""))↵
    0.06
    Gam
    0.06
    )):↵
    0.06
    ई
    0.06
     QUEUE
    0.06
    」，
    0.06
    Act Density 0.046%

    No Known Activations