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

    Neuronpedia

    INDEX
    Explanations

    English language text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    君
    -0.06
    ['<{
    -0.06
    during
    -0.06
     Pendant
    -0.06
     derives
    -0.06
     describes
    -0.06
    acies
    -0.06
    anship
    -0.06
    .It
    -0.06
     modify
    -0.06
    POSITIVE LOGITS
     понад
    0.07
     teg
    0.07
    下来
    0.06
     киш
    0.06
     обще
    0.06
    -host
    0.06
     malé
    0.06
     filament
    0.06
    字幕
    0.06
     fic
    0.06
    Act Density 0.000%

    No Known Activations