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

    Neuronpedia

    INDEX
    Explanations

    our

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oup
    -0.08
     attrs
    -0.07
    pler
    -0.07
     Finger
    -0.07
     alarms
    -0.06
     Choir
    -0.06
    чить
    -0.06
    velop
    -0.06
    in
    -0.06
    Secondary
    -0.06
    POSITIVE LOGITS
    ブリ
    0.07
    'Neill
    0.06
    .esp
    0.06
    423
    0.06
    _UNICODE
    0.06
     sayesinde
    0.06
     detainees
    0.06
    _sender
    0.06
     Meals
    0.06
     připoj
    0.06
    Act Density 0.004%

    No Known Activations