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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kosher
    -0.06
    -ind
    -0.06
     indispens
    -0.06
    顯
    -0.06
    	raw
    -0.06
     paginate
    -0.06
    unas
    -0.05
     전에
    -0.05
    .plugins
    -0.05
     Activity
    -0.05
    POSITIVE LOGITS
    _SRV
    0.08
    自己的
    0.07
    .Make
    0.07
    |
    0.07
    ])]
    0.07
    _MASK
    0.07
    ,"
    0.07
     "/"↵
    0.07
    ancements
    0.07
    )|
    0.06
    Act Density 0.042%

    No Known Activations