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

    Neuronpedia

    INDEX
    Explanations

    guideline updates and revisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resurrection
    -0.07
     canyon
    -0.06
     मश
    -0.06
     آباد
    -0.06
    가능
    -0.06
     tabBar
    -0.05
     bullshit
    -0.05
     Rise
    -0.05
    _UI
    -0.05
     retaining
    -0.05
    POSITIVE LOGITS
    oner
    0.07
    _enqueue
    0.07
     увагу
    0.07
    izu
    0.07
     transmissions
    0.07
    ート
    0.07
    _keeper
    0.07
     divid
    0.06
    �
    0.06
    алов
    0.06
    Act Density 0.020%

    No Known Activations