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

    Neuronpedia

    INDEX
    Explanations

    flame

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aptic
    -0.07
    .INTER
    -0.07
     slipping
    -0.07
     Bur
    -0.07
     SID
    -0.07
    .Css
    -0.06
     pInfo
    -0.06
     slips
    -0.06
     spying
    -0.06
    [loc
    -0.06
    POSITIVE LOGITS
     Flame
    0.09
     flame
    0.08
     façon
    0.07
     emblem
    0.06
    lam
    0.06
    (ent
    0.06
     영상
    0.06
    alm
    0.06
    得到
    0.06
    -manager
    0.06
    Act Density 0.005%

    No Known Activations