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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ause
    -0.08
    Heel
    -0.08
    Metadata
    -0.08
     decorar
    -0.07
    렛
    -0.07
     duct
    -0.07
     украш
    -0.07
    .dtd
    -0.07
     retailer
    -0.07
    -та
    -0.07
    POSITIVE LOGITS
     erine
    0.08
     nier
    0.08
     principali
    0.08
     основных
    0.07
     naast
    0.07
     strategies
    0.07
     विभिन्न
    0.07
     byg
    0.07
     jasa
    0.07
     يعد
    0.07
    Act Density 0.003%

    No Known Activations