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

    Neuronpedia

    INDEX
    Explanations

    your ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CDF
    1.06
     Ellie
    1.06
    Riley
    1.02
     Tipper
    1.00
     Tipp
    1.00
     IAA
    0.98
     Roundup
    0.98
     Fortuna
    0.98
     TCU
    0.97
    ifact
    0.95
    POSITIVE LOGITS
    _
    1.83
     _
    1.29
    _"
    1.13
     '_
    1.12
     "_
    1.07
    ('_
    1.07
    _)
    1.07
    ._
    1.07
    \_
    1.06
    _'
    1.05
    Act Density 1.343%

    No Known Activations