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

    Neuronpedia

    INDEX
    Explanations

    time periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     northwest
    -0.07
     folding
    -0.07
     있었다
    -0.07
     repeatedly
    -0.06
    <num
    -0.06
    sorting
    -0.06
     companies
    -0.06
    _LOGGER
    -0.06
     including
    -0.06
     |/
    -0.06
    POSITIVE LOGITS
     Preview
    0.06
    	state
    0.06
    verification
    0.06
    (rule
    0.06
     Buch
    0.06
    bytes
    0.06
    OBJECT
    0.06
    ByName
    0.06
    letes
    0.06
     Sanct
    0.06
    Act Density 0.100%

    No Known Activations