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

    Neuronpedia

    INDEX
    Explanations

    Spilling incidents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     republice
    -0.06
     entails
    -0.06
     renewed
    -0.06
    .metadata
    -0.06
    センター
    -0.06
     coastal
    -0.06
    nějších
    -0.06
     getchar
    -0.06
    時の
    -0.06
    .URI
    -0.06
    POSITIVE LOGITS
    .addTo
    0.06
     élect
    0.06
    roc
    0.06
    ulares
    0.06
     rencontrer
    0.06
    SELL
    0.06
     示
    0.06
    oto
    0.06
    OTO
    0.06
    kv
    0.06
    Act Density 0.013%

    No Known Activations