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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وو
    -0.07
     �
    -0.06
    иту
    -0.06
    .Remove
    -0.06
     aggregated
    -0.06
    มากกว
    -0.06
    _CODEC
    -0.06
     Clash
    -0.06
     Besides
    -0.06
    Describe
    -0.06
    POSITIVE LOGITS
     applaud
    0.07
    imizi
    0.07
     chilly
    0.06
     henüz
    0.06
    شماری
    0.06
     stay
    0.06
     $\
    0.06
     essen
    0.06
     Indy
    0.06
     checkout
    0.06
    Act Density 0.016%

    No Known Activations