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

    Neuronpedia

    INDEX
    Explanations

    code, paths, errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    负责
    -0.07
    есь
    -0.06
    (exports
    -0.06
    OO
    -0.06
    mination
    -0.06
     ει
    -0.06
     analogous
    -0.05
     \"%
    -0.05
    坂
    -0.05
    courses
    -0.05
    POSITIVE LOGITS
    ؟
    0.09
    حص
    0.07
    àng
    0.07
     bef
    0.07
     skirm
    0.07
     thunk
    0.07
    Execution
    0.06
     Nội
    0.06
     roi
    0.06
    ilit
    0.06
    Act Density 0.082%

    No Known Activations