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

    Neuronpedia

    INDEX
    Explanations

    cycle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LEC
    -0.07
    Cls
    -0.06
    ADOS
    -0.06
     Emoji
    -0.06
     backpage
    -0.06
    owany
    -0.06
     설정
    -0.06
     cuales
    -0.06
     maman
    -0.06
    Bot
    -0.06
    POSITIVE LOGITS
     Modifier
    0.07
    比例
    0.07
    全面
    0.07
     renewables
    0.06
    .Length
    0.06
    riend
    0.06
    ]=>
    0.06
    รด
    0.06
    Dear
    0.06
     sooner
    0.06
    Act Density 0.005%

    No Known Activations