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

    Neuronpedia

    INDEX
    Explanations

    `document.documentElement.`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eller
    0.44
    dt
    0.39
     মদ
    0.38
    水位
    0.38
    NotEmpty
    0.38
    eltic
    0.37
    ”
    0.37
    ”!
    0.36
    upper
    0.36
     niiden
    0.36
    POSITIVE LOGITS
    она
    0.44
     синд
    0.44
     geodes
    0.44
     план
    0.43
    डिशा
    0.42
     aphids
    0.42
    нан
    0.42
     एफ
    0.42
     Excluding
    0.42
    齙
    0.41
    Act Density 0.000%

    No Known Activations