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

    Neuronpedia

    INDEX
    Explanations

    Describing articles/books

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cinema
    -0.07
    UB
    -0.07
     Including
    -0.07
    akespeare
    -0.06
     locale
    -0.06
    倘
    -0.06
     über
    -0.06
    ᡞ
    -0.06
    _ng
    -0.06
     women
    -0.06
    POSITIVE LOGITS
    -messages
    0.08
    arsers
    0.07
    وط
    0.07
     Shuttle
    0.07
    =".
    0.07
    าน
    0.07
     государ
    0.07
     Mobility
    0.07
     shar
    0.07
     Lage
    0.06
    Act Density 0.032%

    No Known Activations