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

    Neuronpedia

    INDEX
    Explanations

    rules

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /module
    -0.07
    _queue
    -0.07
     IPS
    -0.07
    /gpio
    -0.07
    vature
    -0.07
    members
    -0.07
    anime
    -0.07
    _MB
    -0.07
    nię
    -0.07
    _cookies
    -0.07
    POSITIVE LOGITS
    但也
    0.08
    弟弟
    0.07
     sino
    0.07
    瑜
    0.07
    据说
    0.07
    alt
    0.07
    ilt
    0.07
    rå
    0.07
    .g
    0.07
     work
    0.07
    Act Density 0.022%

    No Known Activations