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

    Neuronpedia

    INDEX
    Explanations

    `to` followed by `deal` or `addAction`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Contest
    -0.76
    話題
    -0.69
    currentPage
    -0.68
    timestamp
    -0.65
    leftrightarrow
    -0.64
    contro
    -0.62
     czę
    -0.62
    Ф
    -0.62
    kwargs
    -0.61
    Contr
    -0.61
    POSITIVE LOGITS
     Ui
    0.78
    etus
    0.75
    Nose
    0.70
    iedział
    0.68
    DONT
    0.68
     NEC
    0.67
     mémoire
    0.67
     Devine
    0.66
    diep
    0.66
     descente
    0.65
    Act Density 0.052%

    No Known Activations