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

    Neuronpedia

    INDEX
    Explanations

    aggregation/fibr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    correct
    -0.07
     stud
    -0.07
    Number
    -0.07
     Anim
    -0.06
     Moon
    -0.06
    /pop
    -0.06
     Cap
    -0.06
     cap
    -0.06
     gui
    -0.06
    Pressed
    -0.06
    POSITIVE LOGITS
     Anglo
    0.06
     cơm
    0.06
    �
    0.06
    从
    0.06
    μαι
    0.06
     становить
    0.06
     Higgins
    0.06
     confidently
    0.06
    'ex
    0.06
     Episcopal
    0.06
    Act Density 0.011%

    No Known Activations