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

    Neuronpedia

    INDEX
    Explanations

    name and age fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NUM
    0.41
    CHANG
    0.39
    ).*
    0.38
    minute
    0.38
    уда
    0.38
    second
    0.36
    varphi
    0.36
    Lawrence
    0.36
    SECOND
    0.35
    ).-
    0.35
    POSITIVE LOGITS
     BadRequest
    0.44
     Ubuy
    0.42
     شده
    0.42
     ainsi
    0.42
     න
    0.41
    typicode
    0.41
     કંપની
    0.41
    몰
    0.41
     gde
    0.41
     Equity
    0.40
    Act Density 0.070%

    No Known Activations