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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dictionary
    -0.06
     nip
    -0.06
     restrained
    -0.06
    .IMAGE
    -0.06
    creating
    -0.06
    टर
    -0.06
    _five
    -0.06
    FileType
    -0.06
    IsActive
    -0.06
    civil
    -0.06
    POSITIVE LOGITS
     Edmonton
    0.07
    (Exception
    0.06
     Ramirez
    0.06
    exus
    0.06
     dział
    0.06
    ्फ
    0.06
     дом
    0.06
     onu
    0.06
    」の
    0.06
    /met
    0.06
    Act Density 0.130%

    No Known Activations