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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    34
    -0.07
    KO
    -0.07
    37
    -0.07
    namese
    -0.07
     Verizon
    -0.06
     kịp
    -0.06
    ۳
    -0.06
    7
    -0.06
     uno
    -0.06
     서로
    -0.06
    POSITIVE LOGITS
     August
    0.09
     May
    0.08
    May
    0.08
     June
    0.07
     March
    0.07
     January
    0.07
    June
    0.07
    August
    0.07
     baked
    0.06
     July
    0.06
    Act Density 0.015%

    No Known Activations