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

    Neuronpedia

    INDEX
    Explanations

    Instructions, how-to guides

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Interest
    -0.08
    睛
    -0.07
     Nine
    -0.07
    _supply
    -0.07
     trader
    -0.06
     reef
    -0.06
    婆
    -0.06
     interest
    -0.06
    year
    -0.06
     registrar
    -0.06
    POSITIVE LOGITS
    verture
    0.06
     POSSIBILITY
    0.06
    ."','".$
    0.06
     Coming
    0.06
    먹
    0.06
     由
    0.06
    .addEventListener
    0.06
     وقتی
    0.06
     MQTT
    0.06
     ViewBag
    0.06
    Act Density 0.018%

    No Known Activations