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

    Neuronpedia

    INDEX
    Explanations

    common sequence starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stitution
    0.50
    dataSource
    0.49
    mal
    0.47
    st
    0.47
     साइन
    0.47
    werte
    0.47
    ात
    0.46
    lığını
    0.46
    lini
    0.46
    umumkan
    0.46
    POSITIVE LOGITS
    ಟ್‌
    0.47
    ్యాచ్
    0.44
     Rhino
    0.43
     freshest
    0.43
     Optimizer
    0.42
     quickest
    0.42
     Halb
    0.42
     Sau
    0.41
     Beer
    0.41
     Gough
    0.41
    Act Density 0.002%

    No Known Activations