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

    Neuronpedia

    INDEX
    Explanations

    lama/llama

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /details
    -0.07
    Purple
    -0.07
     gardens
    -0.07
     gan
    -0.07
    第一次
    -0.07
    osition
    -0.07
     occurred
    -0.06
    池
    -0.06
     vibrating
    -0.06
    其中
    -0.06
    POSITIVE LOGITS
    .LA
    0.06
    .setMax
    0.06
     Draco
    0.06
    .WRITE
    0.06
     Evan
    0.06
    lama
    0.06
    ::::::::::::::::::::::::::::::::
    0.06
     LTC
    0.06
     miles
    0.06
    /groups
    0.06
    Act Density 0.004%

    No Known Activations