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

    Neuronpedia

    INDEX
    Explanations

    citation numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     becoming
    0.94
     become
    0.85
     -
    0.81
     Become
    0.79
     becomes
    0.75
     getting
    0.70
    "-
    0.69
    `-
    0.69
    ్యూ
    0.69
    -$
    0.69
    POSITIVE LOGITS
    cited
    1.13
     cited
    1.12
     citado
    1.02
    xiii
    0.89
     cite
    0.88
     cites
    0.86
     гуляць
    0.83
    citing
    0.83
     Cited
    0.80
     citing
    0.80
    Act Density 0.045%

    No Known Activations