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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Imp
    -0.07
     supervision
    -0.07
    _request
    -0.07
    .imp
    -0.07
    _default
    -0.06
     impartial
    -0.06
    _IMPORT
    -0.06
     speeches
    -0.06
     zap
    -0.06
     Red
    -0.06
    POSITIVE LOGITS
     categories
    0.06
    /is
    0.06
     의해
    0.06
     augmented
    0.06
     slab
    0.06
     beware
    0.06
    ющее
    0.06
     DAMAGE
    0.06
    findById
    0.06
     Degrees
    0.05
    Act Density 0.016%

    No Known Activations