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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    like
    -0.08
    Muslim
    -0.07
    Once
    -0.07
     emerging
    -0.07
    ):↵
    -0.06
     Fleet
    -0.06
     Harper
    -0.06
    (Html
    -0.06
     واس
    -0.06
     financed
    -0.06
    POSITIVE LOGITS
    鐘
    0.06
     пункт
    0.06
     một
    0.06
    _PE
    0.06
    ifikace
    0.06
    InputModule
    0.06
    .history
    0.06
    Tên
    0.06
    ние
    0.06
     Copies
    0.06
    Act Density 0.086%

    No Known Activations