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

    Neuronpedia

    INDEX
    Explanations

    is called

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     that
    0.66
    ),
    0.61
     (=
    0.59
    !
    0.59
     which
    0.57
    )
    0.56
    ;
    0.55
    ()
    0.53
     }
    0.52
    ).
    0.52
    POSITIVE LOGITS
     reactivation
    0.63
     preclinical
    0.62
     synergistic
    0.62
     triathlon
    0.62
    ገኛ
    0.62
     peacekeeping
    0.61
     aberrant
    0.61
     hypothalamic
    0.60
     pediatric
    0.60
     powertrain
    0.58
    Act Density 0.038%

    No Known Activations