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

    Neuronpedia

    INDEX
    Explanations

    curiosity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     레벨
    -0.07
    rá
    -0.07
     Ike
    -0.06
     monsters
    -0.06
    otoxic
    -0.06
    責
    -0.06
     Ping
    -0.06
     haciendo
    -0.06
    =p
    -0.06
     Tiger
    -0.06
    POSITIVE LOGITS
    Interested
    0.07
    _MACRO
    0.06
     APPLY
    0.06
     chained
    0.06
     fetchData
    0.06
    Appro
    0.06
     видов
    0.06
     Common
    0.06
    /db
    0.06
     consequential
    0.06
    Act Density 0.013%

    No Known Activations