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

    Neuronpedia

    INDEX
    Explanations

    ratios between terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    掝
    0.49
    㫴
    0.48
    沺
    0.46
     ಉಪ
    0.45
    goài
    0.44
    ख्य
    0.44
     اخت
    0.44
     బ్యా
    0.43
    ofer
    0.43
     padi
    0.43
    POSITIVE LOGITS
     cautionary
    0.46
     कॉंग्रेस
    0.45
     Drama
    0.44
    ด
    0.44
     trade
    0.43
    日
    0.43
     unim
    0.43
    2
    0.43
     Jerry
    0.42
    Z
    0.42
    Act Density 0.000%

    No Known Activations