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

    Neuronpedia

    INDEX
    Explanations

    degrees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .valueOf
    -0.07
    ories
    -0.07
    .byId
    -0.07
    アニメ
    -0.06
    iosper
    -0.06
     CSRF
    -0.06
    ibt
    -0.06
    Boxes
    -0.06
    scp
    -0.06
    (IT
    -0.06
    POSITIVE LOGITS
     degrees
    0.10
     dire
    0.08
    "+"
    0.07
     premiere
    0.07
     جه
    0.07
     Regular
    0.07
     Degrees
    0.07
     disagrees
    0.07
    discover
    0.06
     Erdogan
    0.06
    Act Density 0.005%

    No Known Activations