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

    Neuronpedia

    INDEX
    Explanations

    cooking preparation steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     analysed
    0.76
    baum
    0.71
     analyse
    0.71
     synonymous
    0.68
     actually
    0.68
    analyse
    0.68
    analyses
    0.67
    weet
    0.66
     analysis
    0.65
     actual
    0.65
    POSITIVE LOGITS
    箅
    0.87
     convection
    0.85
    ORIENTATION
    0.82
     Preheat
    0.82
    ットフォーム
    0.80
    铺
    0.79
    鎏
    0.78
     plates
    0.78
    flatiron
    0.78
    MARGIN
    0.77
    Act Density 0.426%

    No Known Activations