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

    Neuronpedia

    INDEX
    Explanations

    call on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     There
    0.82
     Another
    0.79
    There
    0.76
     This
    0.75
     Presumably
    0.75
     provided
    0.75
     Provided
    0.74
     These
    0.73
    Another
    0.72
     Further
    0.71
    POSITIVE LOGITS
    咊
    0.78
     soooo
    0.73
    {$\
    0.72
     sooo
    0.71
     kontroller
    0.71
     všech
    0.71
    闓
    0.69
     BBM
    0.69
    {-\
    0.69
     réglementation
    0.68
    Act Density 0.000%

    No Known Activations