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

    Neuronpedia

    INDEX
    Explanations

    consumption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.62
     unknownFields
    -0.60
    inerja
    -0.56
     calculées
    -0.50
    eadilan
    -0.49
    Hentet
    -0.47
    utilisons
    -0.46
     Paglinawan
    -0.45
    reszcie
    -0.45
    tigo
    -0.45
    POSITIVE LOGITS
     Pater
    0.60
    úgó
    0.59
    riwal
    0.58
    pread
    0.57
    τιά
    0.56
     étrangers
    0.56
    󠁢
    0.56
     étranger
    0.55
     Pogba
    0.54
    (!__
    0.54
    Act Density 0.005%

    No Known Activations