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

    Neuronpedia

    INDEX
    Explanations

    Team

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    技术人员
    -0.07
    树脂
    -0.06
     Interpreter
    -0.06
     Earn
    -0.06
    历来
    -0.06
    债务
    -0.06
     qualification
    -0.06
    这首歌
    -0.06
    	Service
    -0.06
    قبول
    -0.06
    POSITIVE LOGITS
    ByPrimaryKey
    0.07
     When
    0.07
     annon
    0.07
    (rule
    0.07
    commended
    0.06
     eigentlich
    0.06
    鄅
    0.06
    (TR
    0.06
    !!↵
    0.06
     cheat
    0.06
    Act Density 0.000%

    No Known Activations