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

    Neuronpedia

    INDEX
    Explanations

    Announcements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _RETURNTRANSFER
    -0.07
    mailto
    -0.07
     kh
    -0.07
     přest
    -0.06
    .fromJson
    -0.06
     Diego
    -0.06
    QUENCE
    -0.06
    ur
    -0.06
     XX
    -0.06
     Eva
    -0.06
    POSITIVE LOGITS
     getConfig
    0.07
    지요
    0.06
     Hij
    0.06
    orianCalendar
    0.06
    ��
    0.06
    richt
    0.06
     classe
    0.06
     Obl
    0.06
     말을
    0.06
    xaa
    0.06
    Act Density 0.082%

    No Known Activations