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

    Neuronpedia

    INDEX
    Explanations

    regard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EV
    -0.07
     Bur
    -0.07
     รอง
    -0.07
     která
    -0.06
    -0.06
    .part
    -0.06
     vaping
    -0.06
    TI
    -0.06
     contestant
    -0.06
     "#{
    -0.06
    POSITIVE LOGITS
    ерах
    0.09
    BACK
    0.07
    Monad
    0.06
     dál
    0.06
     optimal
    0.06
    šak
    0.06
    perl
    0.06
    ARATION
    0.06
     delegation
    0.06
     Whilst
    0.06
    Act Density 0.005%

    No Known Activations