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

    Neuronpedia

    INDEX
    Explanations

    ational

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     üy
    -0.07
    Transition
    -0.06
    Immediate
    -0.06
    GU
    -0.06
    _dataset
    -0.06
    .CL
    -0.06
    WATCH
    -0.06
     wing
    -0.06
    ScrollView
    -0.06
    ная
    -0.06
    POSITIVE LOGITS
    -produ
    0.07
    따
    0.07
     zdję
    0.06
    比赛
    0.06
    #+
    0.06
     επισ
    0.06
    charset
    0.06
    zw
    0.06
     pci
    0.06
     hak
    0.06
    Act Density 0.002%

    No Known Activations