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

    Neuronpedia

    INDEX
    Explanations

    fontsize or name arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dollar
    0.41
    bytes
    0.40
    identifier
    0.39
    引用
    0.39
     tunt
    0.39
    asset
    0.39
    des
    0.38
    dollars
    0.38
    Asset
    0.38
    jail
    0.37
    POSITIVE LOGITS
    例文
    0.42
     playtime
    0.41
     bracelet
    0.40
    သင့်
    0.40
    ొప్పి
    0.40
     confessed
    0.40
     extinct
    0.40
     sweetest
    0.40
    ObjectIndex
    0.40
     mittlerweile
    0.40
    Act Density 0.000%

    No Known Activations