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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     topping
    -0.07
     capac
    -0.06
    ocus
    -0.06
     predicate
    -0.06
    égor
    -0.06
     Recover
    -0.06
    pc
    -0.06
    POINT
    -0.06
    ish
    -0.06
    Disconnected
    -0.06
    POSITIVE LOGITS
     боли
    0.07
    tvrt
    0.06
     ortadan
    0.06
    λευ
    0.06
     ارتف
    0.06
    Quarter
    0.06
    pellier
    0.06
    Digite
    0.06
     andre
    0.06
     tumblr
    0.06
    Act Density 0.055%

    No Known Activations