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

    Neuronpedia

    INDEX
    Explanations

    bronze

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     있고
    -0.07
    locks
    -0.07
    (QL
    -0.07
    lamış
    -0.07
    bersome
    -0.07
    Manage
    -0.07
     segregated
    -0.06
     Surveillance
    -0.06
    okud
    -0.06
    했고
    -0.06
    POSITIVE LOGITS
     İngiliz
    0.06
     recursively
    0.06
     cycl
    0.06
    Portal
    0.06
     зави
    0.06
    istogram
    0.06
    epsilon
    0.06
     odv
    0.06
    _dummy
    0.06
    getInstance
    0.06
    Act Density 0.003%

    No Known Activations