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

    Neuronpedia

    INDEX
    Explanations

    Patent numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Same
    -0.07
    سب
    -0.07
     discard
    -0.07
    okies
    -0.07
    tearDown
    -0.07
     MAY
    -0.07
    حسب
    -0.07
    좇
    -0.07
    עשי
    -0.07
     recommending
    -0.06
    POSITIVE LOGITS
    ('<?
    0.07
    |-
    0.06
    邢
    0.06
    _Int
    0.06
    ⥂
    0.06
    elic
    0.06
    📹
    0.06
     sat
    0.06
    ?!
    0.06
    <tag
    0.06
    Act Density 0.015%

    No Known Activations