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

    Neuronpedia

    INDEX
    Explanations

    brave

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ell
    -0.07
     Ellen
    -0.07
    udget
    -0.07
    _COLL
    -0.07
     millions
    -0.06
     CLEAR
    -0.06
     كامل
    -0.06
    el
    -0.06
     Fold
    -0.06
     cycl
    -0.06
    POSITIVE LOGITS
     brave
    0.16
     Brave
    0.16
     bravery
    0.11
     Braves
    0.09
     Blade
    0.08
    vo
    0.07
    Man
    0.07
    бу
    0.07
     brav
    0.07
     Bravo
    0.07
    Act Density 0.003%

    No Known Activations