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

    Neuronpedia

    INDEX
    Explanations

    dates and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    덴
    0.93
    㝅
    0.87
    0.87
     şi
    0.85
    㡺
    0.85
    িয়াছি
    0.82
     Watercolor
    0.82
     Еще
    0.82
     cổ
    0.81
    성
    0.80
    POSITIVE LOGITS
    jul
    0.71
     personer
    0.65
    arlier
    0.64
     kemungkinan
    0.64
     manipulation
    0.63
     lijst
    0.63
    2
    0.63
     subset
    0.62
    ängen
    0.62
    ים
    0.61
    Act Density 0.001%

    No Known Activations