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

    Neuronpedia

    INDEX
    Explanations

    numbers and calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    רן
    -0.08
     raad
    -0.08
     kumb
    -0.07
    شد
    -0.07
    ̭
    -0.07
     Linda
    -0.07
    Bread
    -0.07
     undercover
    -0.07
    цо
    -0.07
    adden
    -0.07
    POSITIVE LOGITS
     onwards
    0.10
    일부터
    0.09
     onward
    0.09
     Thoughts
    0.09
     Beyond
    0.09
     теле
    0.08
     เป็นต้น
    0.08
    Beyond
    0.08
     beyond
    0.08
     മുതൽ
    0.08
    Act Density 0.044%

    No Known Activations