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

    Neuronpedia

    INDEX
    Explanations

    -Encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     demasi
    -0.07
     بتاريخ
    -0.07
     Coin
    -0.07
    ュ
    -0.07
     homosexuality
    -0.07
     boast
    -0.06
    矛盾
    -0.06
     TRUE
    -0.06
     Angebot
    -0.06
     assigns
    -0.06
    POSITIVE LOGITS
    个赛季
    0.08
     Nigeria
    0.07
    izard
    0.07
     interfere
    0.06
    prints
    0.06
    embali
    0.06
    巨头
    0.06
     ساعات
    0.06
    ータ
    0.06
    -page
    0.06
    Act Density 0.000%

    No Known Activations