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

    Neuronpedia

    INDEX
    Explanations

    write

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مواد
    -0.07
     Hu
    -0.07
     Educational
    -0.06
    čel
    -0.06
    WIDTH
    -0.06
    _BLACK
    -0.06
    has
    -0.06
    -$
    -0.06
    _rel
    -0.06
    .VAL
    -0.06
    POSITIVE LOGITS
     السعودية
    0.07
     Writing
    0.06
     Kaepernick
    0.06
     شعر
    0.06
     okum
    0.06
    ？”
    0.06
     жод
    0.06
    илання
    0.06
    隆
    0.06
     мої
    0.06
    Act Density 0.033%

    No Known Activations