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

    Neuronpedia

    INDEX
    Explanations

    Programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conveying
    -0.09
    еста
    -0.09
     меку
    -0.09
     forwarding
    -0.08
    erat
    -0.08
    養
    -0.08
    િત
    -0.08
     мекун
    -0.08
     પણ
    -0.08
    ിക്ക
    -0.08
    POSITIVE LOGITS
     ABD
    0.09
    른
    0.08
     Schr
    0.08
     Bann
    0.08
    Kad
    0.07
     Kad
    0.07
    .compute
    0.07
     lant
    0.07
     Pec
    0.07
     pregled
    0.07
    Act Density 0.000%

    No Known Activations