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

    Neuronpedia

    INDEX
    Explanations

    Technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (source
    -0.07
    units
    -0.07
    ลาด
    -0.07
     vous
    -0.06
     votre
    -0.06
     Moore
    -0.06
    otros
    -0.06
     ngủ
    -0.06
     ngũ
    -0.06
     distingu
    -0.06
    POSITIVE LOGITS
     tecr
    0.07
    ilage
    0.07
     Tarif
    0.06
    .lifecycle
    0.06
     zeit
    0.06
    _ag
    0.06
     خرد
    0.06
    .Observable
    0.06
     nz
    0.06
     departure
    0.06
    Act Density 0.009%

    No Known Activations