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

    Neuronpedia

    INDEX
    Explanations

    code/database references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -faced
    -0.06
     اینکه
    -0.06
    会
    -0.06
     premise
    -0.06
     incentives
    -0.06
    must
    -0.06
    yní
    -0.06
     antis
    -0.06
     consensus
    -0.06
     respons
    -0.06
    POSITIVE LOGITS
     Тур
    0.08
     значение
    0.08
     Ζ
    0.07
     conquer
    0.07
    英文
    0.07
    صن
    0.07
     gấp
    0.06
     작업
    0.06
    さらに
    0.06
    ίο
    0.06
    Act Density 0.080%

    No Known Activations