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

    Neuronpedia

    INDEX
    Explanations

    Generality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    éal
    -0.07
    migration
    -0.07
    wand
    -0.06
    stan
    -0.06
    programming
    -0.06
     screens
    -0.06
    567
    -0.06
     metrů
    -0.06
     bomb
    -0.06
     downloaded
    -0.06
    POSITIVE LOGITS
     Auto
    0.08
     flexGrow
    0.07
    /octet
    0.06
     非
    0.06
     EntityManager
    0.06
    .Volume
    0.06
    =wx
    0.06
    َو
    0.06
     Pfizer
    0.06
     เจ
    0.06
    Act Density 0.018%

    No Known Activations