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

    Neuronpedia

    INDEX
    Explanations

    Mathematical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scams
    -0.07
    instruction
    -0.07
     accidents
    -0.07
    .syntax
    -0.07
    Senior
    -0.07
     primaryStage
    -0.07
     screened
    -0.07
    _SCHEMA
    -0.07
    центр
    -0.06
    郵
    -0.06
    POSITIVE LOGITS
     UserInfo
    0.07
    礼物
    0.06
    .addAll
    0.06
    属性
    0.06
     "+
    0.06
    Info
    0.06
    _decoder
    0.06
    ISCO
    0.06
     Worth
    0.06
     الو
    0.06
    Act Density 0.006%

    No Known Activations