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

    Neuronpedia

    INDEX
    Explanations

    "the" followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tends
    0.41
    mostly
    0.37
     aligns
    0.37
    For
    0.36
     contends
    0.36
     জন্যে
    0.35
    샵
    0.35
     provides
    0.34
     `>=`,
    0.34
     prácticamente
    0.34
    POSITIVE LOGITS
     XNUMX
    0.64
     aforementioned
    0.60
     entire
    0.52
     slightest
    0.52
     embankment
    0.50
    mselves
    0.50
     same
    0.49
     Himalayas
    0.48
     viciss
    0.48
     opponent
    0.47
    Act Density 0.007%

    No Known Activations