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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hu
    -0.07
    Hu
    -0.06
     anarchist
    -0.06
    iswa
    -0.06
    Su
    -0.06
    699
    -0.06
     kuk
    -0.06
    üsseldorf
    -0.06
    radio
    -0.06
    ']}</
    -0.06
    POSITIVE LOGITS
    personal
    0.06
    朝
    0.06
     dlg
    0.06
     Courtesy
    0.06
     Align
    0.06
    .targets
    0.06
     antig
    0.06
     كانت
    0.06
    ederal
    0.06
    quiries
    0.06
    Act Density 0.156%

    No Known Activations