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

    Neuronpedia

    INDEX
    Explanations

    online services

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     artisans
    -0.08
     substrate
    -0.07
     targeting
    -0.06
    /Footer
    -0.06
     Associ
    -0.06
     ortak
    -0.06
    .Linear
    -0.06
     deputy
    -0.06
    وروب
    -0.06
    .FromArgb
    -0.06
    POSITIVE LOGITS
     russe
    0.07
    чай
    0.06
    ΙΚ
    0.06
     supp
    0.06
    ью
    0.06
     يونيو
    0.06
    ummy
    0.06
    ыш
    0.06
     와
    0.05
    �
    0.05
    Act Density 0.023%

    No Known Activations