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

    Neuronpedia

    INDEX
    Explanations

    code and special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     edeb
    -0.06
    �
    -0.06
     representing
    -0.06
     гост
    -0.06
    Whats
    -0.06
    дем
    -0.06
     таб
    -0.06
     penchant
    -0.06
     totalmente
    -0.06
    そう
    -0.06
    POSITIVE LOGITS
    ΕΡ
    0.07
    rophy
    0.07
     ）
    0.07
    oso
    0.07
    .offset
    0.06
    .width
    0.06
    (ib
    0.06
    .touches
    0.06
    中学
    0.06
    ;a
    0.06
    Act Density 0.000%

    No Known Activations