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

    Neuronpedia

    INDEX
    Explanations

    math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Γεω
    -0.07
    aturally
    -0.06
     exciting
    -0.06
    สม
    -0.06
    ابه
    -0.06
     youths
    -0.06
     yeah
    -0.06
     loung
    -0.06
     realized
    -0.06
     lighten
    -0.06
    POSITIVE LOGITS
     xmlDoc
    0.08
     stays
    0.07
    (sr
    0.07
    PNG
    0.07
     معد
    0.06
     ваг
    0.06
     SCIP
    0.06
    .FontStyle
    0.06
    (sound
    0.06
    0.06
    Act Density 0.005%

    No Known Activations