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

    Neuronpedia

    INDEX
    Explanations

    comments and reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tero
    0.41
    രോ
    0.38
    たす
    0.37
    "^
    0.36
    InBuffer
    0.36
     pls
    0.35
    мут
    0.35
    рово
    0.35
    畑
    0.35
     ప్రశ్న
    0.33
    POSITIVE LOGITS
     comments
    0.49
    comments
    0.47
    REPORT
    0.46
    comment
    0.43
    Comments
    0.43
     मेथ
    0.42
    댓글
    0.42
     मानस
    0.41
     коммента
    0.40
    ishop
    0.40
    Act Density 0.000%

    No Known Activations