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

    Neuronpedia

    INDEX
    Explanations

    Awareness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    担任
    -0.08
    Введите
    -0.07
     mathematics
    -0.07
    inz
    -0.07
    ClassLoader
    -0.06
    rax
    -0.06
    nosis
    -0.06
     ppm
    -0.06
     rin
    -0.06
    中华民族
    -0.06
    POSITIVE LOGITS
     tranqu
    0.07
    衎
    0.07
     Święt
    0.07
     존
    0.07
    .Use
    0.07
    놨
    0.07
    蔷
    0.06
    (ext
    0.06
    那只
    0.06
     vec
    0.06
    Act Density 0.034%

    No Known Activations