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

    Neuronpedia

    INDEX
    Explanations

    lots of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beispielsweise
    0.47
     hingegen
    0.43
     similarly
    0.43
     எவ்வாறு
    0.41
    ਏ
    0.38
    其
    0.38
    겪
    0.38
     relates
    0.38
     এরূপ
    0.37
     যেরূপ
    0.37
    POSITIVE LOGITS
     lots
    1.12
     plenty
    1.09
    lots
    0.95
    Lots
    0.87
     occasional
    0.85
     Lots
    0.84
    Plenty
    0.83
     endless
    0.79
     Plenty
    0.79
     enough
    0.77
    Act Density 0.029%

    No Known Activations