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

    Neuronpedia

    INDEX
    Explanations

    parts or sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     careless
    0.76
     व्यू
    0.72
     fonctionnalité
    0.71
    луйста
    0.71
     hidrául
    0.70
    "]);
    0.70
     உறுப்பின
    0.68
    itorios
    0.67
    ehir
    0.67
     最後
    0.67
    POSITIVE LOGITS
     따르면
    0.70
    gab
    0.70
    Na
    0.65
     Böl
    0.65
    Ls
    0.64
    lb
    0.63
     সুরে
    0.63
     মাকে
    0.63
    Sub
    0.62
    Being
    0.62
    Act Density 0.446%

    No Known Activations