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

    Neuronpedia

    INDEX
    Explanations

    a bit nuanced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chances
    0.82
     duro
    0.79
    лама
    0.78
     pampered
    0.78
    と感じ
    0.76
    с
    0.75
    হ্ন
    0.73
    ты
    0.71
     typhoid
    0.71
     titrated
    0.71
    POSITIVE LOGITS
     Artwork
    0.73
    Lieutenant
    0.72
    optional
    0.71
    AN
    0.68
     Headers
    0.68
    Developer
    0.65
    og
    0.65
    Manager
    0.64
     대한
    0.64
     Monitors
    0.64
    Act Density 0.001%

    No Known Activations