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

    Neuronpedia

    INDEX
    Explanations

    Machiavelli

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (con
    -0.07
     Instructor
    -0.07
    玱
    -0.07
     demasi
    -0.07
    =C
    -0.07
     isConnected
    -0.06
    新闻记者
    -0.06
     Bucc
    -0.06
     acronym
    -0.06
     plum
    -0.06
    POSITIVE LOGITS
    督查
    0.07
    HY
    0.06
     motivate
    0.06
    0.06
     burglary
    0.06
     ح
    0.06
     thực
    0.06
    옥
    0.06
     looph
    0.06
     approving
    0.06
    Act Density 0.001%

    No Known Activations