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

    Neuronpedia

    INDEX
    Explanations

    betting on price changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    കാശ
    0.54
    ເຮັດ
    0.52
    𒌨
    0.50
    િવસ
    0.49
     impoverished
    0.48
     Wikipedia
    0.48
     Atari
    0.48
     ব্রাজ
    0.47
     참
    0.46
     حوال
    0.46
    POSITIVE LOGITS
    {
    0.61
    \
    0.60
    3
    0.55
    ות
    0.54
    ↵↵
    0.52
     autonom
    0.47
    o
    0.46
    י
    0.45
    走
    0.45
    ני
    0.45
    Act Density 0.000%

    No Known Activations