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

    Neuronpedia

    INDEX
    Explanations

    greetings and introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Control
    0.79
    Elim
    0.74
    Organic
    0.73
    맨
    0.70
    Http
    0.69
    Organ
    0.69
    coordinated
    0.69
    封
    0.69
    Delete
    0.68
    mature
    0.67
    POSITIVE LOGITS
     name
    0.80
     nome
    0.74
    做什么
    0.72
     genus
    0.72
     permisos
    0.71
     chiamato
    0.71
     appelée
    0.71
     um
    0.71
     Nice
    0.70
     puis
    0.70
    Act Density 0.279%

    No Known Activations