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

    Neuronpedia

    INDEX
    Explanations

    added code lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Akshay
    0.52
     attendre
    0.52
     Controllers
    0.50
     omdat
    0.50
     ECONOMIC
    0.50
     HCN
    0.48
     Economía
    0.48
    स्थापन
    0.48
     çünkü
    0.48
     Міні
    0.47
    POSITIVE LOGITS
    ，
    0.61
    ﺒ
    0.57
     a
    0.57
     C
    0.55
    Never
    0.55
    }$.
    0.53
    中で
    0.53
    <0xE5>
    0.52
    ucaly
    0.51
     U
    0.50
    Act Density 0.000%

    No Known Activations