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

    Neuronpedia

    INDEX
    Explanations

    between

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stitch
    0.85
    暊
    0.81
    遇到的
    0.80
     conditioner
    0.78
    钰
    0.77
    莗
    0.77
     stitching
    0.77
    㡱
    0.74
    centroid
    0.71
     downloader
    0.70
    POSITIVE LOGITS
    ន្ត
    0.81
    rockets
    0.64
    iteta
    0.63
    ophora
    0.63
    가를
    0.62
     lối
    0.61
    يام
    0.60
    бурга
    0.60
     আর্কাইভ
    0.59
    gaia
    0.59
    Act Density 0.002%

    No Known Activations