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

    Neuronpedia

    INDEX
    Explanations

    so, however, but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Without
    0.39
     vooral
    0.39
    Notably
    0.39
    Txt
    0.39
     belangrijk
    0.38
     وهذه
    0.38
    Ultimately
    0.38
    Calories
    0.37
     claramente
    0.37
    Diese
    0.37
    POSITIVE LOGITS
    unless
    0.86
    除非
    0.85
     unless
    0.82
     Unless
    0.80
     except
    0.79
     Exceptions
    0.78
     Except
    0.75
     exceptions
    0.74
     However
    0.74
     HOWEVER
    0.73
    Act Density 0.270%

    No Known Activations