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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mush
    -0.06
    PRS
    -0.06
     baseUrl
    -0.06
    _counters
    -0.06
     чт
    -0.06
    //================================================
    -0.06
    ilere
    -0.06
    sur
    -0.06
    .typ
    -0.06
    にも
    -0.06
    POSITIVE LOGITS
     açı
    0.08
     norge
    0.07
     advisor
    0.07
    NOW
    0.07
    ôme
    0.07
     advised
    0.06
    yaw
    0.06
     coincidence
    0.06
     Tender
    0.06
    -placement
    0.06
    Act Density 0.031%

    No Known Activations