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

    Neuronpedia

    INDEX
    Explanations

    studied

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hud
    -0.08
     exagger
    -0.08
     Nes
    -0.07
     encompass
    -0.07
    容器
    -0.07
     Circular
    -0.07
     Cable
    -0.07
    elic
    -0.07
     kneeling
    -0.07
    电视
    -0.07
    POSITIVE LOGITS
    ريق
    0.07
    -inverse
    0.07
    [attr
    0.07
     persone
    0.07
    上有
    0.07
     Associate
    0.07
    -order
    0.07
    _CHANGE
    0.07
    ⾵
    0.07
     Spirit
    0.06
    Act Density 0.050%

    No Known Activations