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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (mon
    -0.07
     リ
    -0.06
    leştir
    -0.06
    bubble
    -0.06
    ley
    -0.06
    teki
    -0.06
    Mon
    -0.06
    Men
    -0.06
     my
    -0.06
    credit
    -0.06
    POSITIVE LOGITS
     брос
    0.07
     />,
    0.06
     Highlands
    0.06
     salts
    0.06
    .toolStripSeparator
    0.06
    HING
    0.06
     Suggestions
    0.06
     vyp
    0.06
    航
    0.06
     serta
    0.06
    Act Density 0.020%

    No Known Activations