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

    Neuronpedia

    INDEX
    Explanations

    Code and technical specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     txt
    -0.07
     tooltips
    -0.07
    _fast
    -0.06
    ection
    -0.06
     چنین
    -0.06
    	right
    -0.06
    commended
    -0.06
    (normal
    -0.06
     ημέ
    -0.06
    	list
    -0.06
    POSITIVE LOGITS
    boy
    0.07
     rav
    0.06
    -is
    0.06
    ěti
    0.06
    ateria
    0.06
     similarities
    0.06
    rections
    0.06
    ौल
    0.06
    шов
    0.06
    _sl
    0.06
    Act Density 0.212%

    No Known Activations