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

    Neuronpedia

    INDEX
    Explanations

    searching

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igsaw
    -0.07
     �
    -0.07
     куб
    -0.06
     alıyor
    -0.06
     dabei
    -0.06
     policing
    -0.06
    701
    -0.06
     بيانات
    -0.06
    dbname
    -0.06
    结
    -0.06
    POSITIVE LOGITS
    одав
    0.07
     βα
    0.07
    .default
    0.07
     puppet
    0.06
    manage
    0.06
     started
    0.06
     >(
    0.06
    ังหว
    0.06
     ;-
    0.06
     #
    0.06
    Act Density 0.018%

    No Known Activations