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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lickr
    -0.08
    ugar
    -0.08
     mult
    -0.08
    .ReactNode
    -0.07
    李某
    -0.07
     나는
    -0.07
     Poland
    -0.07
    eña
    -0.07
    uento
    -0.07
    重庆
    -0.07
    POSITIVE LOGITS
    𫄧
    0.07
    -ra
    0.07
     Skin
    0.07
    تحالف
    0.06
    tres
    0.06
     orgasm
    0.06
    edis
    0.06
    玄
    0.06
     Projectile
    0.06
    (Build
    0.06
    Act Density 0.016%

    No Known Activations