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

    Neuronpedia

    INDEX
    Explanations

    named entities or data

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    귤
    0.55
     hepatocytes
    0.54
    脑袋
    0.54
    题材
    0.54
    bab
    0.54
     Vamp
    0.52
     उभ
    0.52
     bab
    0.51
     मौलिक
    0.51
     ലീ
    0.51
    POSITIVE LOGITS
     downsides
    0.64
    之外
    0.61
     downwards
    0.58
     outwards
    0.58
    外
    0.58
    setActive
    0.58
    мед
    0.58
     immediatamente
    0.58
     undesired
    0.57
     outskirts
    0.57
    Act Density 0.000%

    No Known Activations