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

    Neuronpedia

    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aud
    -0.07
    ��
    -0.07
    (obj
    -0.07
    _hosts
    -0.07
    Pressed
    -0.07
     Squad
    -0.06
    thin
    -0.06
     Leader
    -0.06
    addin
    -0.06
    _dest
    -0.06
    POSITIVE LOGITS
    กฎหมาย
    0.07
     Bảo
    0.06
     факти
    0.06
     значительно
    0.06
     ('$
    0.06
     [],
↵
    0.06
    $body
    0.06
     Ngọc
    0.06
    ทาง
    0.06
    $form
    0.06
    Act Density 0.012%

    No Known Activations