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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reported
    -0.07
    ë
    -0.07
    ®,
    -0.07
     alerted
    -0.06
    σωπ
    -0.06
     Grocery
    -0.06
    	conf
    -0.06
    factory
    -0.06
    flash
    -0.06
     recounted
    -0.06
    POSITIVE LOGITS
     ZERO
    0.07
     सह
    0.07
    ičky
    0.06
    �
    0.06
    求
    0.06
    彻
    0.06
     fácil
    0.06
    _ASCII
    0.06
    #{
    0.06
    장
    0.06
    Act Density 0.013%

    No Known Activations