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

    Neuronpedia

    INDEX
    Explanations

    storage box

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     using
    0.46
     lumens
    0.40
     Engineered
    0.38
    根本
    0.38
     Industries
    0.38
     Automotive
    0.36
     lumen
    0.36
     Fabric
    0.36
     with
    0.35
     fabric
    0.35
    POSITIVE LOGITS
    irteenth
    0.49
     Geschenk
    0.40
    𒁹
    0.40
     gifting
    0.39
    çant
    0.38
     Zeitschr
    0.38
     선물
    0.38
    ỏ
    0.38
    ické
    0.38
    Hepin
    0.37
    Act Density 0.002%

    No Known Activations