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

    Neuronpedia

    INDEX
    Explanations

    15

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prisons
    -0.07
    bus
    -0.07
    Kids
    -0.06
    -navigation
    -0.06
    خاص
    -0.06
    featured
    -0.06
    >Hello
    -0.06
    久久
    -0.06
    .bus
    -0.06
     echo
    -0.06
    POSITIVE LOGITS
    (meta
    0.07
    WF
    0.07
     forn
    0.07
    کاران
    0.07
    ونا
    0.07
     Con
    0.06
     ///</
    0.06
    .GetInstance
    0.06
     fixture
    0.06
     consume
    0.06
    Act Density 0.000%

    No Known Activations