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

    Neuronpedia

    INDEX
    Explanations

    known for its

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    åller
    0.70
     배치
    0.69
    வராய்
    0.63
    偻
    0.63
    ançais
    0.62
    निर
    0.61
    ਗਾ
    0.61
    ourg
    0.61
     ihtiy
    0.61
     महंगाई
    0.60
    POSITIVE LOGITS
     famous
    4.59
    famous
    4.08
     famed
    3.96
     renowned
    3.80
     famoso
    3.79
     known
    3.74
     famosa
    3.70
     Famous
    3.70
    Famous
    3.69
     terkenal
    3.58
    Act Density 0.545%

    No Known Activations