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

    Neuronpedia

    INDEX
    Explanations

    providing or receiving information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '
    -2.84
     "
    -2.78
    '
    -2.77
    </b>
    -2.55
     "(
    -2.34
     "'
    -2.22
     Teilen
    -2.16
     somber
    -2.16
     ezek
    -2.14
    i
    -2.14
    POSITIVE LOGITS
    .
    3.98
    袮
    2.91
    踅
    2.80
    玧
    2.67
    .")
    2.61
     itſelf
    2.58
    喼
    2.52
     muft
    2.50
    2.42
    綃
    2.42
    Act Density 0.006%

    No Known Activations