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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     durations
    -0.06
     :↵↵
    -0.06
    "';↵
    -0.06
    \Annotation
    -0.06
    (order
    -0.06
     Králové
    -0.06
     traders
    -0.06
    _TWO
    -0.06
    ,Integer
    -0.06
     wilderness
    -0.06
    POSITIVE LOGITS
    __(
    0.07
    yh
    0.07
     Peg
    0.07
    гляд
    0.07
    tered
    0.06
     ).
    0.06
    ーク
    0.06
     reactor
    0.06
     gelişim
    0.06
    ????????????????
    0.06
    Act Density 0.011%

    No Known Activations