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

    Neuronpedia

    INDEX
    Explanations

    mathematical sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     designate
    -0.08
    NULL
    -0.07
     workforce
    -0.07
    :block
    -0.07
     NULL
    -0.07
    abled
    -0.07
     delays
    -0.07
    (dispatch
    -0.07
    -0.07
     legislative
    -0.07
    POSITIVE LOGITS
     Dara
    0.09
     conservation
    0.08
     ịhụ
    0.08
     Conservation
    0.08
     recurr
    0.08
     Baxter
    0.08
    ♡
    0.08
     Hiro
    0.08
     Wolfs
    0.08
     Roller
    0.08
    Act Density 0.014%
    No Known Activations