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

    Neuronpedia

    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ооруж
    -0.07
     bast
    -0.07
     empleado
    -0.07
     taskId
    -0.07
    .listFiles
    -0.07
     баз
    -0.06
     Bast
    -0.06
    傍
    -0.06
    FE
    -0.06
    フ
    -0.06
    POSITIVE LOGITS
     Person
    0.08
    要么
    0.07
     ✓
    0.07
    य
    0.07
    etime
    0.07
    姐
    0.07
    .strptime
    0.07
    Cookies
    0.07
    ENTION
    0.07
     winters
    0.07
    Act Density 0.020%

    No Known Activations