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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     breath
    -0.07
    itor
    -0.07
     src
    -0.07
    arya
    -0.06
    ='"+
    -0.06
     erg
    -0.06
     BaseService
    -0.06
     文件
    -0.06
     Pir
    -0.06
    ，可
    -0.06
    POSITIVE LOGITS
    .listener
    0.07
    .ReadString
    0.06
     pathway
    0.06
    \Action
    0.06
    _plain
    0.06
     주문
    0.06
    /m
    0.06
    'order
    0.06
    preview
    0.06
    ●●
    0.06
    Act Density 0.044%

    No Known Activations