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

    Neuronpedia

    INDEX
    Explanations

    say "for"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     değildir
    -0.07
    ر
    -0.06
     sahiptir
    -0.06
    ロ
    -0.06
    .Topic
    -0.06
    San
    -0.06
    .navigateTo
    -0.06
    uuml
    -0.06
     六
    -0.06
     healthier
    -0.06
    POSITIVE LOGITS
     BG
    0.07
     ns
    0.06
    演
    0.06
     RX
    0.06
     황
    0.06
     rain
    0.06
    ––
    0.06
     trend
    0.06
    _nt
    0.06
     arreglo
    0.06
    Act Density 0.047%

    No Known Activations