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

    Neuronpedia

    INDEX
    Explanations

    contrastive conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.37
     а
    0.35
     CGRectMake
    0.34
    '
    0.34
    すると
    0.31
    ?
    0.31
     alebo
    0.31
     ή
    0.31
    ),
    0.30
    -
    0.30
    POSITIVE LOGITS
     dennoch
    0.44
    仍
    0.40
     nevertheless
    0.38
     trotzdem
    0.38
     nonetheless
    0.36
    ยังมี
    0.35
    依然
    0.34
     stále
    0.33
    Nevertheless
    0.33
    有不少
    0.33
    Act Density 0.069%

    No Known Activations