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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dogs
    -0.06
    ,strlen
    -0.06
    >M
    -0.06
     بده
    -0.06
     investigation
    -0.06
     好
    -0.06
    >You
    -0.06
    Sur
    -0.06
    nul
    -0.06
    شتر
    -0.06
    POSITIVE LOGITS
    RESS
    0.07
    .guard
    0.06
    ्मच
    0.06
    Conv
    0.06
     collectively
    0.06
    Was
    0.06
    (it
    0.06
     rank
    0.06
    (..
    0.06
    eneration
    0.06
    Act Density 0.034%

    No Known Activations