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

    Neuronpedia

    INDEX
    Explanations

    evaluating options and alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suele
    0.42
     suelen
    0.41
    most
    0.38
    ుడు
    0.38
    vrdr
    0.38
    requently
    0.38
     majeure
    0.37
     असते
    0.37
    resu
    0.37
     عادة
    0.37
    POSITIVE LOGITS
     options
    0.99
     alternatives
    0.91
     possibility
    0.90
     possibilities
    0.90
     possibilidade
    0.88
     alternative
    0.86
     možnosti
    0.86
     alternativas
    0.85
     possibilidades
    0.84
     mogelijkheden
    0.84
    Act Density 0.070%

    No Known Activations