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

    Neuronpedia

    INDEX
    Explanations

    wiki URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ahmedabad
    0.75
    anol
    0.74
    ServletException
    0.72
     addTo
    0.69
     Sith
    0.67
    ुट
    0.66
     Pogba
    0.66
    üedad
    0.66
    ரும்பு
    0.66
    permitAll
    0.66
    POSITIVE LOGITS
    మం
    0.82
    álen
    0.79
     lezione
    0.77
    மான
    0.77
    wijs
    0.76
    ចាំ
    0.76
     koncept
    0.76
     चाहिँ
    0.75
     }+\
    0.74
     situazione
    0.74
    Act Density 0.020%

    No Known Activations