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

    Neuronpedia

    INDEX
    Explanations

    Similar to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ATION
    2.25
    ння
    1.97
    𝘯
    1.89
    тка
    1.74
    ન
    1.70
    ლ
    1.69
    ∞</
    1.68
    ∗</
    1.66
    се
    1.63
    𝘴
    1.62
    POSITIVE LOGITS
    ב
    2.45
    ities
    2.20
    ע
    2.14
    to
    1.97
    その
    1.97
    한
    1.96
    at
    1.87
     misguided
    1.87
     voire
    1.81
    cG
    1.80
    Act Density 0.026%

    No Known Activations