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

    Neuronpedia

    INDEX
    Explanations

    locations and geography

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ЮЛ
    -0.07
    ITHER
    -0.06
     fishes
    -0.06
     y
    -0.06
    -k
    -0.06
    Con
    -0.06
     Sho
    -0.06
    阳
    -0.06
     swung
    -0.06
    (rgb
    -0.06
    POSITIVE LOGITS
     apartheid
    0.07
    skills
    0.06
     Somebody
    0.06
     Mezi
    0.06
     todos
    0.06
     našeho
    0.06
     '--
    0.06
     neon
    0.06
    尿
    0.06
    edor
    0.06
    Act Density 0.043%

    No Known Activations