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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    原创
    -0.07
     Thou
    -0.07
     discretion
    -0.07
    出现
    -0.07
    ジュ
    -0.06
    (rep
    -0.06
    彗
    -0.06
     Dangerous
    -0.06
    精装
    -0.06
    Roy
    -0.06
    POSITIVE LOGITS
    玩意
    0.07
    亲戚
    0.07
     dans
    0.07
     organism
    0.07
    identifier
    0.07
    ither
    0.07
     utilis
    0.07
    otomy
    0.07
     LocalDate
    0.06
     correlate
    0.06
    Act Density 0.001%

    No Known Activations