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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Others
    -0.07
     remnants
    -0.06
     Valley
    -0.06
     Three
    -0.06
    COMMON
    -0.06
     Patton
    -0.06
     Dev
    -0.06
     NAMES
    -0.06
     balls
    -0.06
     王
    -0.06
    POSITIVE LOGITS
    eting
    0.07
    러운
    0.07
     развития
    0.06
    allax
    0.06
    -таки
    0.06
    プ
    0.06
    вищ
    0.06
     Flexible
    0.06
    การต
    0.06
    .FileInputStream
    0.06
    Act Density 0.009%

    No Known Activations