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

    Neuronpedia

    INDEX
    Explanations

    Code, string manipulation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LABEL
    -0.07
     yak
    -0.07
     Gand
    -0.06
     Ker
    -0.06
    scenes
    -0.06
    >Your
    -0.06
     diner
    -0.06
    Creates
    -0.06
     Bust
    -0.06
    ových
    -0.06
    POSITIVE LOGITS
    ',
↵
    0.07
    \x
    0.06
     člov
    0.06
    ’int
    0.06
     denotes
    0.06
    ｀ヽ
    0.06
    ;');↵
    0.06
     υπ
    0.06
    <context
    0.06
    .UR
    0.06
    Act Density 0.051%

    No Known Activations