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

    Neuronpedia

    INDEX
    Explanations

    Ruby classes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ographies
    -0.07
    TEMPLATE
    -0.07
    "One
    -0.07
    _header
    -0.06
    lient
    -0.06
     reservation
    -0.06
    egrity
    -0.06
    App
    -0.06
     migrations
    -0.06
    _th
    -0.06
    POSITIVE LOGITS
    활동
    0.06
    alary
    0.06
     pron
    0.06
    112
    0.06
    �
    0.06
     왜
    0.06
     proph
    0.06
     rebell
    0.06
    notifications
    0.06
    capt
    0.06
    Act Density 0.011%

    No Known Activations