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

    Neuronpedia

    INDEX
    Explanations

    code comments and annotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fastest
    0.42
    yx
    0.41
     safest
    0.39
     skills
    0.38
     quickest
    0.38
     loyalty
    0.37
     freighter
    0.36
     பிடித்த
    0.36
    fraud
    0.36
    免
    0.36
    POSITIVE LOGITS
    Throughout
    0.92
     Throughout
    0.90
     throughout
    0.84
    注释
    0.84
     komentar
    0.83
     comments
    0.82
     комментария
    0.82
     annotations
    0.80
     commentaires
    0.80
     comentários
    0.78
    Act Density 0.019%

    No Known Activations