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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ">';↵
    -0.07
    .be
    -0.07
    :str
    -0.06
    imagem
    -0.06
    /th
    -0.06
     historians
    -0.06
     Are
    -0.06
     quad
    -0.06
     jsou
    -0.06
    álních
    -0.06
    POSITIVE LOGITS
    ERING
    0.07
     attachments
    0.07
    ção
    0.07
    fu
    0.07
    овал
    0.06
    ering
    0.06
    ẹn
    0.06
     immigr
    0.06
     

↵
    0.06
     classmates
    0.06
    Act Density 0.292%

    No Known Activations