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

    Neuronpedia

    INDEX
    Explanations

    divorce asset division

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     إصدار
    -0.08
     vanish
    -0.08
     vanished
    -0.08
     চাল
    -0.07
     disappeared
    -0.07
    -warning
    -0.07
    ctic
    -0.07
     misterio
    -0.07
    mono
    -0.07
    idot
    -0.07
    POSITIVE LOGITS
     tijdens
    0.10
     principles
    0.09
    原则
    0.09
     Жен
    0.08
     панели
    0.08
     justa
    0.08
    ీలో
    0.08
     jaw
    0.08
    _locations
    0.08
     Principles
    0.08
    Act Density 0.003%

    No Known Activations