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

    Neuronpedia

    INDEX
    Explanations

    breakdowns and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    units
    0.44
    Units
    0.42
    ssr
    0.42
    volumes
    0.42
    감을
    0.41
     ``
    0.41
    car
    0.40
    Soft
    0.40
    vehicles
    0.39
    SSR
    0.38
    POSITIVE LOGITS
    DeviceCompliance
    0.44
    卫生
    0.40
    cadilly
    0.40
    πουργ
    0.40
     bureau
    0.39
     aisle
    0.37
     thwarted
    0.37
     Sagan
    0.36
     wholesome
    0.36
     Pradesh
    0.36
    Act Density 0.002%

    No Known Activations