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

    Neuronpedia

    INDEX
    Explanations

    ->

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skept
    -0.07
    dí
    -0.07
    벨
    -0.06
     needy
    -0.06
     disciplines
    -0.06
        
    -0.06
    _SSL
    -0.06
    ILLE
    -0.06
     bắc
    -0.06
    £o
    -0.06
    POSITIVE LOGITS
     ocup
    0.08
     duel
    0.07
     amount
    0.06
    Generally
    0.06
    Tahoma
    0.06
    inc
    0.06
    +%
    0.06
     Werk
    0.06
     Verg
    0.06
     전체
    0.06
    Act Density 0.014%

    No Known Activations