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

    Neuronpedia

    INDEX
    Explanations

    global followed by a topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    schild
    0.44
     பாத
    0.40
    ھار
    0.38
    enschaft
    0.37
     યો
    0.37
     أمس
    0.36
    abend
    0.36
     وي
    0.35
    estes
    0.35
    斯的
    0.35
    POSITIVE LOGITS
     warming
    0.76
     ग्लोबल
    0.62
     глоба
    0.61
     Warming
    0.60
     Global
    0.59
     global
    0.59
    ளாவ
    0.59
     GLOBAL
    0.58
    GLOBAL
    0.55
     globe
    0.54
    Act Density 0.023%

    No Known Activations