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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    、私
    -0.07
    eného
    -0.07
    년에
    -0.06
    notEmpty
    -0.06
     حالت
    -0.06
     jm
    -0.06
    .newInstance
    -0.06
    ژی
    -0.06
     玩
    -0.06
    olv
    -0.06
    POSITIVE LOGITS
     CHECK
    0.07
    —we
    0.07
    *\
    0.07
    使用
    0.07
     picturesque
    0.06
     must
    0.06
     SCH
    0.06
    cles
    0.06
    *****
↵
    0.06
    Making
    0.06
    Act Density 0.018%

    No Known Activations