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

    Neuronpedia

    INDEX
    Explanations

    historical figures and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maestros
    0.86
     cowboys
    0.82
     Heidi
    0.79
     equipos
    0.78
     percol
    0.77
     Kollegen
    0.77
     பெண்
    0.76
     piccoli
    0.76
     여성
    0.74
     topi
    0.74
    POSITIVE LOGITS
    Ⅶ
    0.97
     II
    0.91
    VII
    0.89
     VII
    0.87
    henius
    0.86
    ̕
    0.86
     הראשון
    0.85
     Saxony
    0.85
    Ⅵ
    0.84
    Ⅱ
    0.84
    Act Density 0.060%

    No Known Activations