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

    Neuronpedia

    INDEX
    Explanations

    necessary inputs and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eventuali
    0.42
     each
    0.39
     attempts
    0.39
     деятельность
    0.39
     faptul
    0.39
    nThe
    0.38
     gelang
    0.37
     esfuerzos
    0.37
    における
    0.36
     எவ்வளவு
    0.36
    POSITIVE LOGITS
     necessária
    0.60
     broadest
    0.55
     necessárias
    0.55
    necessary
    0.54
     requisite
    0.54
     strictest
    0.51
     fewest
    0.51
     nécessaire
    0.49
     necessário
    0.49
     giusta
    0.49
    Act Density 0.157%

    No Known Activations