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

    Neuronpedia

    INDEX
    Explanations

    frequently encountered experiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सरकार
    0.48
    ংখ্যান
    0.47
    资格
    0.46
    द्वी
    0.46
    peasants
    0.46
    वू
    0.46
     otomatik
    0.45
     étages
    0.45
     automatique
    0.45
    ficha
    0.44
    POSITIVE LOGITS
     Metaverse
    0.47
     بهذه
    0.46
    ะ
    0.44
     COVID
    0.42
    :
    0.42
    ע
    0.41
     e
    0.40
    *
    0.39
     ChatGPT
    0.39
     Environmental
    0.39
    Act Density 0.008%

    No Known Activations