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

    Neuronpedia

    INDEX
    Explanations

    Learning and understanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jeffrey
    -0.07
     pode
    -0.06
    ),
↵
    -0.06
     Erik
    -0.06
    対応
    -0.06
    pokemon
    -0.06
    剑
    -0.06
    教授
    -0.06
    ิเศษ
    -0.06
     createdAt
    -0.06
    POSITIVE LOGITS
    ()=>{↵
    0.07
    shortcode
    0.06
     бать
    0.06
    orpor
    0.06
     reperc
    0.06
     TBD
    0.06
    цип
    0.06
     мол
    0.06
     Consequently
    0.06
    ormsg
    0.06
    Act Density 0.069%

    No Known Activations