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

    Neuronpedia

    INDEX
    Explanations

    design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    please
    -0.06
    zw
    -0.06
    standing
    -0.06
     приход
    -0.06
     judged
    -0.06
     certificates
    -0.06
     preparing
    -0.06
     explain
    -0.06
    EXEC
    -0.05
    (char
    -0.05
    POSITIVE LOGITS
     designs
    0.10
     design
    0.07
    getColor
    0.07
     كرة
    0.06
    Secret
    0.06
     speedy
    0.06
     theology
    0.06
    orrow
    0.06
    وتی
    0.06
    ональ
    0.06
    Act Density 0.013%

    No Known Activations