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

    Neuronpedia

    INDEX
    Explanations

    restaurant reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hunters
    -0.07
    ий
    -0.07
     meanings
    -0.07
     torn
    -0.06
     Worlds
    -0.06
    Definitions
    -0.06
    婚
    -0.06
    refer
    -0.06
    (display
    -0.06
    ть
    -0.06
    POSITIVE LOGITS
     frankfurt
    0.06
     compét
    0.06
    %s
    0.06
    .DropDownStyle
    0.06
    .startDate
    0.06
     texas
    0.06
    umbledore
    0.06
     haystack
    0.06
     删除
    0.06
    닉
    0.05
    Act Density 0.029%

    No Known Activations