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

    Neuronpedia

    INDEX
    Explanations

    filtering waste products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $.}
    0.58
    ﺝ
    0.49
    昛
    0.49
    sadquotes
    0.48
     Nasıl
    0.47
     antitumor
    0.46
    纭
    0.46
    ⺈
    0.46
    marshalN
    0.46
    كمة
    0.46
    POSITIVE LOGITS
    ♣
    0.85
    ♠
    0.83
     ♦
    0.80
    ♦
    0.79
    ☎
    0.73
    ♥
    0.62
     ♥
    0.60
    0.58
    w
    0.55
       
    0.54
    Act Density 0.001%

    No Known Activations