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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %/
    -0.06
    .payment
    -0.06
     likelihood
    -0.06
     kB
    -0.06
    _format
    -0.06
     месте
    -0.06
     Appro
    -0.06
     mouseX
    -0.06
     despair
    -0.06
    ();"
    -0.06
    POSITIVE LOGITS
     Darth
    0.07
     Skywalker
    0.07
     Nicaragua
    0.07
    \Twig
    0.06
     того
    0.06
     BÖL
    0.06
    †
    0.06
     ushort
    0.06
     Thames
    0.06
     الجز
    0.06
    Act Density 0.000%

    No Known Activations