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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rugs
    -0.09
    $config
    -0.08
    Trips
    -0.08
     Sweepstakes
    -0.08
    $tmp
    -0.08
     rugs
    -0.08
    ?><
    -0.08
     Greta
    -0.08
    $image
    -0.08
    стит
    -0.07
    POSITIVE LOGITS
     الطرف
    0.08
    0.08
     Blade
    0.07
     muj
    0.07
     VBA
    0.07
     با
    0.07
    ublisher
    0.07
     giver
    0.07
     personalmente
    0.07
     داخل
    0.07
    Act Density 0.002%
    No Known Activations