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

    Neuronpedia

    INDEX
    Explanations

    waving goodbye or back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     =
    0.77
    2
    0.76
    0
    0.73
     parf
    0.70
    。
    0.70
     biliary
    0.68
     globular
    0.66
     р
    0.64
     october
    0.63
     deoxy
    0.63
    POSITIVE LOGITS
    фай
    0.73
    দের
    0.73
    महल
    0.71
    ка
    0.69
    こと
    0.68
    עים
    0.68
    ুস
    0.67
    avacak
    0.66
    ことなく
    0.66
    ু
    0.66
    Act Density 0.002%

    No Known Activations