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

    Neuronpedia

    INDEX
    Explanations

    explaining solutions and complexities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     “
    0.51
    0.50
     Debian
    0.46
     Up
    0.44
    系统
    0.44
     it
    0.44
     Cisco
    0.44
     World
    0.44
     SP
    0.43
    ম্ভ
    0.43
    POSITIVE LOGITS
    hada
    0.53
    𝖗
    0.53
    airobi
    0.49
    🧈
    0.49
    ონი
    0.49
    ന്റി
    0.48
    interno
    0.48
    ਿਰ
    0.46
    raquinone
    0.46
     दैट
    0.46
    Act Density 0.009%

    No Known Activations