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

    Neuronpedia

    INDEX
    Explanations

    game

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arsity
    -0.07
     bapt
    -0.06
     Büyük
    -0.06
     Space
    -0.06
     CHRIST
    -0.06
    olecular
    -0.06
     लग
    -0.06
     рок
    -0.06
    iards
    -0.06
    tir
    -0.06
    POSITIVE LOGITS
    useState
    0.08
     bree
    0.07
     oversee
    0.06
    077
    0.06
    ict
    0.06
    wrapper
    0.06
    NN
    0.06
    apellido
    0.06
    missive
    0.06
     Einstein
    0.06
    Act Density 0.015%

    No Known Activations