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

    Neuronpedia

    INDEX
    Explanations

    analysis, rules, criteria

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     helf
    -0.07
    <Post
    -0.06
     Ala
    -0.06
    azard
    -0.06
     conference
    -0.06
    .head
    -0.06
    Conference
    -0.06
     España
    -0.06
    Ậ
    -0.06
     UICollectionViewCell
    -0.06
    POSITIVE LOGITS
    Once
    0.07
     Once
    0.06
    _users
    0.06
    /assert
    0.06
    ''↵
    0.06
     (£
    0.06
     St
    0.06
    notify
    0.05
    TODO
    0.05
    ापन
    0.05
    Act Density 0.034%

    No Known Activations