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

    Neuronpedia

    INDEX
    Explanations

    yet, but, and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sachen
    0.96
     stuff
    0.93
     상황
    0.90
    /;
    0.89
    -/
    0.87
     grunds
    0.87
     Stuff
    0.87
     식으로
    0.86
     tactics
    0.86
     situatie
    0.83
    POSITIVE LOGITS
     yet
    2.20
    yet
    2.05
    Yet
    1.73
     Yet
    1.70
    且
    1.36
     অথচ
    1.26
    かつ
    1.15
    、
    1.05
    又不
    0.99
     कॉनक
    0.99
    Act Density 0.469%

    No Known Activations