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

    Neuronpedia

    INDEX
    Explanations

    shown

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uele
    -0.07
    vä
    -0.07
    alog
    -0.06
    ecial
    -0.06
     daß
    -0.06
     Ning
    -0.06
    Ρ
    -0.06
    都
    -0.06
    arie
    -0.06
     Fantasy
    -0.06
    POSITIVE LOGITS
     shown
    0.11
    Shown
    0.09
    shown
    0.09
     pinned
    0.08
     그녀
    0.08
    :hidden
    0.07
     protr
    0.07
     shows
    0.07
    .jwt
    0.07
     insign
    0.07
    Act Density 0.010%

    No Known Activations