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

    Neuronpedia

    INDEX
    Explanations

    numbers and people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     retaliation
    -0.07
    ツ
    -0.07
    660
    -0.07
    _Update
    -0.06
     경험
    -0.06
     Enums
    -0.06
    證
    -0.06
    _protocol
    -0.06
     Boulder
    -0.06
    同
    -0.06
    POSITIVE LOGITS
    orgia
    0.07
    )[:
    0.07
    HEME
    0.07
     FEATURES
    0.06
    <i
    0.06
    )',
    0.06
    .''
    0.06
    }))
    0.06
     başlay
    0.06
     kênh
    0.06
    Act Density 0.023%

    No Known Activations