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

    Neuronpedia

    INDEX
    Explanations

    fund and related services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fasteners
    2.95
    ч
    2.81
    ला
    2.75
    ','"+
    2.64
     easements
    2.61
    completely
    2.53
    дить
    2.52
    2.50
    seu
    2.50
    번에
    2.48
    POSITIVE LOGITS
    iin
    3.89
    ம்
    3.55
    y
    3.41
    al
    3.28
    i
    3.22
    es
    3.19
    iere
    3.14
    ar
    3.11
    能
    3.06
    o
    3.05
    Act Density 0.009%

    No Known Activations