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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ཚ
    -0.08
     aviation
    -0.07
    欸
    -0.07
    .isnan
    -0.06
     erotica
    -0.06
    电动汽车
    -0.06
     Oculus
    -0.06
    cast
    -0.06
     Lennon
    -0.06
    旅
    -0.06
    POSITIVE LOGITS
    нятие
    0.09
    hores
    0.07
    ificar
    0.07
    בות
    0.07
     ");↵
    0.07
    уще
    0.07
     amigo
    0.07
    ובת
    0.07
     contato
    0.06
    קיד
    0.06
    Act Density 0.005%

    No Known Activations