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

    Neuronpedia

    INDEX
    Explanations

    writing proposals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ோம்
    0.49
    ണു
    0.48
     cube
    0.47
    㸳
    0.46
     നെറ്റ്‌വർ
    0.44
     remaster
    0.44
     ഹോളി
    0.42
     इस्तेमाल
    0.42
     numbness
    0.42
    सम्म
    0.41
    POSITIVE LOGITS
     proffered
    0.44
    proposal
    0.44
    offer
    0.40
    これは
    0.40
     Acest
    0.39
     this
    0.38
     proposed
    0.38
     explanatory
    0.38
     পাঁচ
    0.38
    ={
    0.37
    Act Density 0.003%

    No Known Activations