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

    Neuronpedia

    INDEX
    Explanations

    control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .best
    -0.07
    xford
    -0.07
    Exporter
    -0.07
     Menschen
    -0.07
    _FAST
    -0.07
     tướng
    -0.06
    ेहतर
    -0.06
    (defun
    -0.06
    .fasterxml
    -0.06
    inho
    -0.06
    POSITIVE LOGITS
     wis
    0.07
    Intersection
    0.07
     Maritime
    0.06
     Committee
    0.06
     Turtle
    0.06
    Policy
    0.06
     contentious
    0.06
    [num
    0.06
    _ads
    0.06
     campground
    0.06
    Act Density 0.012%

    No Known Activations