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

    Neuronpedia

    INDEX
    Explanations

    _impl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Milf
    -0.07
    ACEMENT
    -0.07
    たら
    -0.07
    ergency
    -0.07
     погод
    -0.07
    (collection
    -0.07
    ={['
    -0.06
    acción
    -0.06
    こんな
    -0.06
    Ster
    -0.06
    POSITIVE LOGITS
     lifting
    0.06
     heading
    0.06
     Heading
    0.06
     ､
    0.06
     Crowley
    0.06
    errupt
    0.06
    	table
    0.06
     Debug
    0.06
     Rocket
    0.06
    ackBar
    0.06
    Act Density 0.002%

    No Known Activations