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

    Neuronpedia

    INDEX
    Explanations

    random characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	method
    -0.06
     Estimated
    -0.06
    メ
    -0.06
    รษ
    -0.06
    ABI
    -0.06
     Om
    -0.06
    StartTime
    -0.06
    atoms
    -0.06
     σχε
    -0.06
    /Open
    -0.06
    POSITIVE LOGITS
    γκα
    0.07
    ']]]↵
    0.06
     popcorn
    0.06
    /current
    0.06
    _twitter
    0.06
     bows
    0.06
    :test
    0.06
    -motion
    0.06
    střed
    0.06
     Had
    0.06
    Act Density 0.058%

    No Known Activations