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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <strong
    -0.06
     wonderfully
    -0.06
     lang
    -0.06
    ันน
    -0.06
    чит
    -0.06
     answers
    -0.06
     embarrassing
    -0.06
    Page
    -0.06
     kendine
    -0.06
    ayın
    -0.06
    POSITIVE LOGITS
    ]")↵
    0.07
     manufactures
    0.06
    wine
    0.06
    _UNS
    0.06
    vů
    0.06
    (trace
    0.06
     cartel
    0.06
     uphold
    0.06
    (PyObject
    0.06
    yclerview
    0.06
    Act Density 0.006%

    No Known Activations