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

    Neuronpedia

    INDEX
    Explanations

    sequence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ret
    -0.07
    臨
    -0.07
     cáo
    -0.07
     belli
    -0.07
    kami
    -0.07
    иск
    -0.06
     kháng
    -0.06
    urrection
    -0.06
     RIP
    -0.06
    نان
    -0.06
    POSITIVE LOGITS
    .generated
    0.07
    ują
    0.06
    /gen
    0.06
    -song
    0.06
     الرياض
    0.06
     leaned
    0.06
     jov
    0.06
    _expected
    0.06
    (packet
    0.06
     katkı
    0.06
    Act Density 0.002%

    No Known Activations