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

    Neuronpedia

    INDEX
    Explanations

    various foreign language fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </span>
    0.71
    </b>
    0.66
     fun
    0.64
    </code>
    0.63
    </sup>
    0.63
    </strong>
    0.62
    </sub>
    0.59
     push
    0.58
     }
    0.58
     ton
    0.55
    POSITIVE LOGITS
    nın
    1.20
    wiąz
    1.12
    iéndose
    1.01
    től
    1.00
    ：
    0.98
    कम
    0.93
    bido
    0.92
    ："
    0.92
    ：（
    0.91
    úsica
    0.90
    Act Density 0.803%

    No Known Activations