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

    Neuronpedia

    INDEX
    Explanations

    Time calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    today
    -0.06
    ️
    -0.06
    463
    -0.06
    voice
    -0.06
     heater
    -0.06
    ratings
    -0.06
    press
    -0.06
    $/)
    -0.06
    订单
    -0.06
    —you
    -0.06
    POSITIVE LOGITS
     postup
    0.07
     lightly
    0.06
    čení
    0.06
     ban
    0.06
    .undefined
    0.06
    (serializer
    0.06
     _
↵
    0.06
     LIC
    0.06
     Repo
    0.06
     زمان
    0.06
    Act Density 0.003%

    No Known Activations