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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sudo
    -0.07
    these
    -0.07
     Ubisoft
    -0.07
    明白
    -0.07
    čila
    -0.07
    Пос
    -0.06
     Alman
    -0.06
    (arr
    -0.06
    .Some
    -0.06
    heimer
    -0.06
    POSITIVE LOGITS
    cadena
    0.07
    covering
    0.06
    ческих
    0.06
     PF
    0.06
    を見
    0.06
     oppon
    0.06
     ant
    0.06
     pulmonary
    0.06
     περι
    0.06
    ディ
    0.06
    Act Density 0.086%

    No Known Activations