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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ैग
    -0.07
    ][:
    -0.07
    周收录
    -0.06
     Mapping
    -0.06
    (ui
    -0.06
     ],
    -0.06
     сим
    -0.06
     ):
    -0.06
    琴
    -0.06
    aturing
    -0.06
    POSITIVE LOGITS
     Natasha
    0.07
     buen
    0.07
    /U
    0.07
    372
    0.06
    /weather
    0.06
    _rl
    0.06
     hamburger
    0.06
    応
    0.06
     İnsan
    0.06
    .WebControls
    0.06
    Act Density 0.064%

    No Known Activations