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

    Neuronpedia

    INDEX
    Explanations

    weather

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Experimental
    -0.07
    ראה
    -0.07
     מאות
    -0.07
    拿出
    -0.07
    Naz
    -0.07
     uluslararası
    -0.07
     Destructor
    -0.07
    טכנולוגיה
    -0.07
    facet
    -0.07
    Truth
    -0.07
    POSITIVE LOGITS
     כול
    0.07
     Vill
    0.07
     className
    0.07
    หม
    0.07
     couple
    0.07
    `.↵
    0.06
     —
    0.06
     """
↵
    0.06
    🇲
    0.06
     module
    0.06
    Act Density 0.027%

    No Known Activations