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

    Neuronpedia

    INDEX
    Explanations

    acknowledgment words after comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    却
    0.46
    However
    0.43
    Alternatively
    0.42
    Moreover
    0.41
    Although
    0.39
    否
    0.38
    Includes
    0.38
    较低
    0.38
    卻
    0.38
                          
    0.38
    POSITIVE LOGITS
     alright
    0.82
     Alright
    0.75
     buckle
    0.74
     sounds
    0.70
     okay
    0.66
    那我們
    0.63
     glad
    0.63
    Alright
    0.62
     allons
    0.61
     definitely
    0.61
    Act Density 0.258%

    No Known Activations