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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prod
    -0.07
    Material
    -0.07
    Dry
    -0.06
     simplistic
    -0.06
    REAK
    -0.06
     Warren
    -0.06
    ellt
    -0.06
     Jackson
    -0.06
     título
    -0.06
     Flags
    -0.06
    POSITIVE LOGITS
     odom
    0.07
    utherland
    0.06
    .getNode
    0.06
     bä
    0.06
    lr
    0.06
    斗
    0.06
    кової
    0.06
    推荐
    0.06
     pars
    0.06
    ียวก
    0.06
    Act Density 0.007%

    No Known Activations