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

    Neuronpedia

    INDEX
    Explanations

    heads or tails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    许多
    0.43
    ancies
    0.42
    很难
    0.42
    TTY
    0.41
    راء
    0.40
    ابقات
    0.40
    年轻人
    0.40
    presumably
    0.40
    cante
    0.40
    destruction
    0.40
    POSITIVE LOGITS
     month
    0.50
     hybrid
    0.49
     <?
    0.48
     {{
    0.48
     pond
    0.47
     glac
    0.47
     склон
    0.47
     <?=
    0.47
     lodging
    0.46
     day
    0.45
    Act Density 0.001%

    No Known Activations