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

    Neuronpedia

    INDEX
    Explanations

    Facebook

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <double
    -0.08
     casing
    -0.08
     bleaching
    -0.08
    出了
    -0.08
     meats
    -0.08
     twice
    -0.07
     Calculates
    -0.07
     माना
    -0.07
     nating
    -0.07
     zweimal
    -0.07
    POSITIVE LOGITS
     forums
    0.15
    Forums
    0.12
     Forums
    0.12
     форум
    0.11
    论坛
    0.11
    交流群
    0.11
     debates
    0.10
     comunidades
    0.10
     forum
    0.10
    論壇
    0.10
    Act Density 0.013%

    No Known Activations