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

    Neuronpedia

    INDEX
    Explanations

    journal article citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zdrav
    -0.07
     tic
    -0.07
    Refreshing
    -0.07
    acades
    -0.06
     RU
    -0.06
    肃
    -0.06
    쿠
    -0.06
    फ
    -0.06
     lx
    -0.06
     Rin
    -0.06
    POSITIVE LOGITS
     animals
    0.07
     исключ
    0.06
     disposed
    0.06
    bra
    0.06
     tasted
    0.06
     decoded
    0.06
     ens
    0.06
     mnoho
    0.06
    abee
    0.06
     discuss
    0.06
    Act Density 0.003%

    No Known Activations