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

    Neuronpedia

    INDEX
    Explanations

    prices subject to change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    似乎
    0.42
    ੌ
    0.39
    0.39
    𝚣
    0.38
    이라면
    0.38
    пар
    0.36
     insurmountable
    0.36
     procesu
    0.36
     smartly
    0.36
    我们也
    0.36
    POSITIVE LOGITS
    あくまで
    1.09
     may
    0.78
     disclaimer
    0.78
    อาจ
    0.75
    may
    0.73
     Disclaimer
    0.68
     subject
    0.67
    可能会
    0.67
    subject
    0.66
    Disclaimer
    0.66
    Act Density 0.034%

    No Known Activations