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

    Neuronpedia

    INDEX
    Explanations

    conflict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _feats
    -0.07
    пос
    -0.07
    -tool
    -0.07
     Coco
    -0.06
    maktan
    -0.06
    Ware
    -0.06
    race
    -0.06
     Госп
    -0.06
     vai
    -0.06
     )
↵
    -0.06
    POSITIVE LOGITS
     ="
    0.07
     Calcium
    0.06
    _owner
    0.06
     pressure
    0.06
    .distance
    0.06
     accum
    0.06
     cultivating
    0.06
    (reply
    0.06
    .Dto
    0.06
     Βα
    0.06
    Act Density 0.025%

    No Known Activations