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

    Neuronpedia

    INDEX
    Explanations

    discussion and debate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eş
    -0.06
     omdat
    -0.06
     flavorful
    -0.06
    Priority
    -0.06
    .MM
    -0.06
     HOUSE
    -0.06
     dirty
    -0.06
    _items
    -0.06
    هور
    -0.06
    acity
    -0.06
    POSITIVE LOGITS
    وی
    0.07
    Sid
    0.06
     Supern
    0.06
    apiKey
    0.06
     yeterli
    0.06
     Log
    0.06
    stice
    0.06
    ya
    0.06
    arious
    0.06
    celik
    0.06
    Act Density 0.137%

    No Known Activations