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

    Neuronpedia

    INDEX
    Explanations

    Singlish and other interjections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     혹은
    0.87
    ac
    0.76
    ad
    0.75
    iéndose
    0.73
     clínica
    0.72
    ы
    0.71
    andez
    0.70
     जिसके
    0.70
    க்கொண்டு
    0.70
     السابقه
    0.70
    POSITIVE LOGITS
    1
    0.91
    larını
    0.85
    ρα
    0.77
    l
    0.73
    ך
    0.71
    <0x84>
    0.69
    ни
    0.69
    p
    0.69
    ва
    0.68
    negara
    0.67
    Act Density 0.001%

    No Known Activations