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

    Neuronpedia

    INDEX
    Explanations

    man pages formatting codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emer
    -0.07
     sớm
    -0.07
     Huck
    -0.06
    zbek
    -0.06
     Reyes
    -0.06
     спіль
    -0.06
    재
    -0.06
    ayout
    -0.06
    mob
    -0.06
    자인
    -0.06
    POSITIVE LOGITS
     ABOUT
    0.06
    ightly
    0.06
     sections
    0.06
    �除
    0.06
    �
    0.06
     placing
    0.06
     nost
    0.06
    وسی
    0.06
     labels
    0.06
     Animals
    0.06
    Act Density 0.001%

    No Known Activations