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

    Neuronpedia

    INDEX
    Explanations

    give you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     경우가
    0.88
     Discussions
    0.86
    Για
    0.83
     quedando
    0.83
     طے
    0.81
     கூறினார்
    0.81
     verkrij
    0.80
    創新
    0.79
     дослі
    0.78
    ιστή
    0.78
    POSITIVE LOGITS
     rise
    1.47
     examples
    1.33
     birth
    1.28
     credit
    1.27
     credence
    1.20
     permission
    1.18
     leeway
    1.17
     thumbs
    1.15
     feedback
    1.09
    rise
    1.09
    Act Density 0.181%

    No Known Activations