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

    Neuronpedia

    INDEX
    Explanations

    sentences starting with pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     optimized
    0.45
     extensible
    0.41
     refined
    0.41
     zoomed
    0.41
    的话
    0.40
    ӵ
    0.40
    padded
    0.40
     catered
    0.40
     optimised
    0.40
     focused
    0.39
    POSITIVE LOGITS
     There
    0.99
     Everyone
    0.80
     This
    0.79
     They
    0.77
     Scientists
    0.77
     It
    0.76
     Unfortunately
    0.75
     Experts
    0.75
     Anyone
    0.74
     You
    0.74
    Act Density 1.033%

    No Known Activations