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

    Neuronpedia

    INDEX
    Explanations

    resources for support or information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fl
    0.70
     susu
    0.54
     unspecified
    0.52
     cot
    0.51
     mop
    0.51
     runny
    0.51
    ent
    0.51
     determinate
    0.51
     pre
    0.49
     hanya
    0.49
    POSITIVE LOGITS
     Stanford
    1.17
     Harvard
    1.15
     Smithsonian
    1.05
     Forbes
    1.03
     специалисты
    0.99
     Professors
    0.99
     Dartmouth
    0.98
     специалистов
    0.96
     Experts
    0.95
     számos
    0.95
    Act Density 0.102%

    No Known Activations