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

    Neuronpedia

    INDEX
    Explanations

    Public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (now
    -0.08
     Jen
    -0.07
    ensing
    -0.07
     digits
    -0.06
     sie
    -0.06
    guess
    -0.06
     breastfeeding
    -0.06
    adam
    -0.06
    )=>{↵
    -0.06
    δόν
    -0.06
    POSITIVE LOGITS
    caught
    0.07
    ancial
    0.06
     Κυ
    0.06
    _epsilon
    0.06
    ulk
    0.06
    lanır
    0.06
     compile
    0.06
     GenerationType
    0.06
     prevailing
    0.06
     feasible
    0.06
    Act Density 0.002%

    No Known Activations