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

    Neuronpedia

    INDEX
    Explanations

    difficulty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bom
    -0.06
     Pax
    -0.06
    nex
    -0.06
    bum
    -0.06
    external
    -0.06
     Tracking
    -0.06
     Mov
    -0.06
     precious
    -0.06
     *_
    -0.06
     hor
    -0.05
    POSITIVE LOGITS
     difficulty
    0.13
     difficulties
    0.10
     trouble
    0.07
    uteč
    0.07
    하지
    0.07
    IDI
    0.07
     har
    0.07
    utherford
    0.07
    iculty
    0.07
     Griffith
    0.07
    Act Density 0.007%

    No Known Activations