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

    Neuronpedia

    INDEX
    Explanations

    video

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chore
    -0.07
     Carb
    -0.07
    מלי
    -0.07
     dummy
    -0.07
     event
    -0.07
     öde
    -0.07
     colourful
    -0.07
    兒童
    -0.06
    _inc
    -0.06
     Doch
    -0.06
    POSITIVE LOGITS
    法律规定
    0.08
    asons
    0.07
    anded
    0.07
    世界一流
    0.07
    Ax
    0.06
     AO
    0.06
     tang
    0.06
    أسل
    0.06
    ガイド
    0.06
    قطع
    0.06
    Act Density 0.033%

    No Known Activations