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

    Neuronpedia

    INDEX
    Explanations

    default states and kingdoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आवा
    0.50
     खा
    0.49
     fórm
    0.49
     afsl
    0.49
    itió
    0.48
     onslaught
    0.48
    ให้กับ
    0.47
    សម្រាប់ការ
    0.47
    closures
    0.46
     relevante
    0.46
    POSITIVE LOGITS
    В
    0.47
    V
    0.46
    А
    0.46
    ヴェ
    0.45
    ッジ
    0.44
    હ
    0.44
    エンジン
    0.43
    J
    0.43
    」
    0.42
    "
    0.42
    Act Density 0.001%

    No Known Activations