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

    Neuronpedia

    INDEX
    Explanations

    LLM model, category, division

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     _
    0.55
     _.
    0.48
     Notre
    0.46
    Notre
    0.44
     Kaplan
    0.44
    Gc
    0.43
     Mrs
    0.43
     Gartner
    0.42
     Das
    0.42
     Joyce
    0.41
    POSITIVE LOGITS
    ческие
    0.56
    ਪ
    0.51
     afect
    0.51
    presentasikan
    0.50
    ικής
    0.49
    াচ্ছে
    0.48
     ज़्यादा
    0.47
     શા
    0.47
    λα
    0.47
     besitzen
    0.46
    Act Density 0.000%

    No Known Activations