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

    Neuronpedia

    INDEX
    Explanations

    single-celled organisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Session
    0.59
     +
    0.56
     gente
    0.56
    are
    0.55
     engl
    0.54
    ן
    0.54
     -
    0.53
    Clouds
    0.53
     Year
    0.52
     e
    0.51
    POSITIVE LOGITS
    ה
    0.91
    د
    0.90
    ر
    0.80
    یت
    0.76
    ه
    0.75
    ר
    0.72
    ن
    0.72
    ایی
    0.69
    قیم
    0.67
     کاهش
    0.66
    Act Density 0.001%

    No Known Activations