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

    Neuronpedia

    INDEX
    Explanations

    closing parentheses and brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ma
    0.48
    adien
    0.40
    ượu
    0.39
    ๓
    0.39
     levens
    0.38
    აძ
    0.38
    ại
    0.38
     новой
    0.38
    ༣
    0.38
     финан
    0.38
    POSITIVE LOGITS
     schemes
    0.36
     سپس
    0.35
    桻
    0.35
     audience
    0.35
     microtubules
    0.35
     rot
    0.34
     floods
    0.34
    گیری
    0.34
     complexes
    0.34
     maupun
    0.34
    Act Density 0.247%

    No Known Activations