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

    Neuronpedia

    INDEX
    Explanations

    medium and blogs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pri
    0.46
     Pri
    0.43
     Prisoners
    0.42
     ($
    0.41
     पह
    0.40
    呎
    0.40
     ⭐
    0.39
     Blade
    0.38
     pri
    0.38
     причин
    0.38
    POSITIVE LOGITS
    Medium
    0.96
     Medium
    0.94
     medium
    0.93
     MEDIUM
    0.85
     blog
    0.82
    medium
    0.80
    MEDIUM
    0.73
     blogs
    0.71
    blog
    0.70
    Blog
    0.69
    Act Density 0.014%

    No Known Activations