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

    Neuronpedia

    INDEX
    Explanations

    elevated areas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .before
    -0.07
     string
    -0.06
     wow
    -0.06
    doctor
    -0.06
     Spit
    -0.06
    ुल
    -0.06
    (mock
    -0.06
    (';
    -0.06
    eç
    -0.06
     ~/
    -0.06
    POSITIVE LOGITS
     trotz
    0.07
     recuper
    0.07
     interception
    0.06
     hodnot
    0.06
     blacks
    0.06
    �
    0.06
     ITEMS
    0.06
    _mi
    0.06
     конт
    0.06
     Baldwin
    0.06
    Act Density 0.040%

    No Known Activations