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

    Neuronpedia

    INDEX
    Explanations

    usr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    토토
    -0.07
    従
    -0.07
    ським
    -0.06
     jedním
    -0.06
     Hamas
    -0.06
     White
    -0.06
    emás
    -0.06
    _personal
    -0.06
     CHAPTER
    -0.06
     anchor
    -0.06
    POSITIVE LOGITS
     duplication
    0.07
    	me
    0.07
    شو
    0.06
     locked
    0.06
    rotch
    0.06
     osp
    0.06
    pra
    0.06
    "?↵↵
    0.06
    romo
    0.06
    ش
    0.06
    Act Density 0.000%

    No Known Activations