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

    Neuronpedia

    INDEX
    Explanations

    usage policies and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bamberger
    0.41
    ментом
    0.39
     परिस्थित
    0.38
     waxes
    0.38
    澜
    0.38
     TECHNIQUES
    0.36
    Ephemeral
    0.36
     শি
    0.36
     टीमें
    0.36
    榀
    0.36
    POSITIVE LOGITS
    rights
    0.43
    jarah
    0.41
    borrow
    0.40
     copyright
    0.38
    使用
    0.38
     pledging
    0.37
    copyright
    0.37
    usage
    0.37
    awards
    0.36
    otch
    0.36
    Act Density 0.000%

    No Known Activations