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

    Neuronpedia

    INDEX
    Explanations

    apostrophes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fateful
    0.42
     actionable
    0.39
     দ্য
    0.39
     eLearning
    0.38
    <unused2199>
    0.38
     fancy
    0.37
     eBooks
    0.37
     supernatural
    0.35
     downsizing
    0.35
     दट
    0.35
    POSITIVE LOGITS
     Ak
    0.62
     Mal
    0.59
     Mor
    0.59
     Ar
    0.58
     K
    0.57
     Bal
    0.57
     S
    0.57
     Bel
    0.57
     Kal
    0.55
     Mar
    0.55
    Act Density 0.682%

    No Known Activations