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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nergie
    -0.07
    ニュ
    -0.07
    iki
    -0.07
    ians
    -0.07
    ik
    -0.06
     constitution
    -0.06
    ฿
    -0.06
    ss
    -0.06
    Ћ
    -0.06
     thích
    -0.06
    POSITIVE LOGITS
     Strat
    0.08
    .stage
    0.07
    0.07
    Weapon
    0.07
    交叉
    0.07
     roadway
    0.07
     RA
    0.07
    与时俱
    0.07
     Oaks
    0.07
     outr
    0.07
    Act Density 0.013%

    No Known Activations