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

    Neuronpedia

    INDEX
    Explanations

    controlling, fell, CEC

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mangiare
    0.44
     тобто
    0.42
     trắng
    0.40
     tornare
    0.39
     yemek
    0.39
    }}\\
    0.38
    bsen
    0.38
     pagare
    0.38
    arit
    0.37
    /*'
    0.37
    POSITIVE LOGITS
     INTERNAL
    0.43
     Shalom
    0.41
     Raster
    0.39
     RESOURCES
    0.39
    แนว
    0.39
     assessments
    0.39
     halo
    0.39
     expert
    0.38
     downloads
    0.38
     RES
    0.38
    Act Density 0.000%

    No Known Activations