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

    Neuronpedia

    INDEX
    Explanations

    AttributeSet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Create
    -0.07
     Mad
    -0.06
    馬
    -0.06
    Shortcut
    -0.06
    housing
    -0.06
     ineff
    -0.06
     sarc
    -0.06
    Escape
    -0.06
    <Point
    -0.06
     स
    -0.06
    POSITIVE LOGITS
     Focus
    0.08
     Hamilton
    0.07
     EK
    0.07
     LoginForm
    0.07
     kWh
    0.06
     Every
    0.06
    _environment
    0.06
     eser
    0.06
    _macros
    0.06
     Lorem
    0.06
    Act Density 0.005%

    No Known Activations