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

    Neuronpedia

    INDEX
    Explanations

    END

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Locator
    -0.07
     allowances
    -0.07
    -chat
    -0.07
    าง
    -0.07
     Brushes
    -0.07
    ائ
    -0.06
     squeeze
    -0.06
    ilim
    -0.06
    angu
    -0.06
     삼성
    -0.06
    POSITIVE LOGITS
     ortadan
    0.07
     Francois
    0.06
     أع
    0.06
     muže
    0.06
    火
    0.06
    ycles
    0.06
    =[],
    0.06
     ventured
    0.06
    piel
    0.06
     же
    0.06
    Act Density 0.001%

    No Known Activations