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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     center
    -0.06
     outer
    -0.06
    Notifications
    -0.06
     compan
    -0.05
     chief
    -0.05
     viewing
    -0.05
     Nightmare
    -0.05
     limit
    -0.05
     bomber
    -0.05
     trickle
    -0.05
    POSITIVE LOGITS
    �
    0.07
     isNew
    0.07
     pthread
    0.07
    _slot
    0.07
    inea
    0.06
     telah
    0.06
    createClass
    0.06
    dag
    0.06
    racak
    0.06
    subpackage
    0.06
    Act Density 0.080%

    No Known Activations