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

    Neuronpedia

    INDEX
    Explanations

    sine purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সময়ে
    0.57
     पता
    0.56
     ደቂ
    0.51
     razão
    0.50
     distancing
    0.50
     brainstorming
    0.50
     বাচ্চ
    0.49
    につきまして
    0.49
    šenje
    0.49
     lavoratori
    0.49
    POSITIVE LOGITS
    س
    0.56
    <0xE3>
    0.51
    种种
    0.49
    ंक
    0.47
    unks
    0.47
    ount
    0.47
    oches
    0.46
    وين
    0.46
    yss
    0.46
    igts
    0.45
    Act Density 0.000%

    No Known Activations