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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    respect
    -0.08
    ládá
    -0.07
     Observ
    -0.06
    Russia
    -0.06
    irebase
    -0.06
    essor
    -0.06
     iteration
    -0.06
     gon
    -0.06
    ee
    -0.06
     Lottery
    -0.06
    POSITIVE LOGITS
    └
    0.07
     कव
    0.07
    374
    0.07
     Zones
    0.06
     diverted
    0.06
    ۶
    0.06
    140
    0.06
     маз
    0.06
     %↵
    0.06
     사건
    0.06
    Act Density 0.068%

    No Known Activations