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

    Neuronpedia

    INDEX
    Explanations

    percent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fır
    -0.07
    _most
    -0.07
     tudo
    -0.07
    etě
    -0.07
    .Dom
    -0.07
    bjerg
    -0.06
    ��
    -0.06
    (plan
    -0.06
    ùy
    -0.06
    айд
    -0.06
    POSITIVE LOGITS
    Absolutely
    0.07
    charts
    0.06
     ).↵↵
    0.06
    .temperature
    0.06
    CREATE
    0.06
    些
    0.06
     lcm
    0.06
    ,↵
    0.06
     Saturn
    0.06
    .↵↵
    0.06
    Act Density 0.024%

    No Known Activations