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

    Neuronpedia

    INDEX
    Explanations

    .wikipedia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đều
    -0.07
    >',
    -0.06
     �
    -0.06
    ---</
    -0.06
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    -0.06
    両
    -0.06
     memor
    -0.06
    �
    -0.06
     Sel
    -0.06
    \\"
    -0.06
    POSITIVE LOGITS
    .wikipedia
    0.13
    #else
    0.06
    。（
    0.06
     steward
    0.06
    term
    0.06
     sodium
    0.06
    riangle
    0.06
    poon
    0.06
    .getResponse
    0.06
     حی
    0.06
    Act Density 0.002%

    No Known Activations