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

    Neuronpedia

    INDEX
    Explanations

    various types of materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     واح
    0.85
     acompanha
    0.82
    इसमें
    0.79
    視
    0.78
     bets
    0.75
    喱
    0.75
     logrado
    0.73
    --------------
    0.72
    ческому
    0.71
    ﹎
    0.71
    POSITIVE LOGITS
    working
    1.01
    anguage
    0.98
    iness
    0.98
    clad
    0.97
     floors
    0.93
    heart
    0.93
     dioxide
    0.89
     monuments
    0.88
    ீரல்
    0.88
    製の
    0.87
    Act Density 0.744%

    No Known Activations