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

    Neuronpedia

    INDEX
    Explanations

    promoting policy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     latitude
    -0.08
    ，由
    -0.06
    \)
    -0.06
     Created
    -0.06
    	AM
    -0.06
    ?>"></
    -0.06
     editar
    -0.06
     ~/
    -0.06
    icts
    -0.06
     Release
    -0.06
    POSITIVE LOGITS
    _secure
    0.07
    _done
    0.07
    ACCEPT
    0.07
    _RESOURCES
    0.06
    oji
    0.06
    rish
    0.06
    랜
    0.06
    /support
    0.06
     accumulating
    0.06
    _MONTH
    0.06
    Act Density 0.051%

    No Known Activations