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

    Neuronpedia

    INDEX
    Explanations

    script tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nejen
    0.56
    不僅
    0.53
    この
    0.45
    不仅
    0.44
    保証
    0.44
    最も
    0.44
    まずは
    0.44
     preconditions
    0.43
    ঠিত
    0.43
     predictability
    0.43
    POSITIVE LOGITS
    x
    0.48
    ဂျ
    0.47
     enthusiasts
    0.46
     concentrates
    0.46
    b
    0.46
    X
    0.46
     ruch
    0.42
     enthusiast
    0.42
     രംഗ
    0.42
    q
    0.42
    Act Density 0.008%

    No Known Activations